[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-deeplearningturkiye--turkce-yapay-zeka-kaynaklari":3,"tool-deeplearningturkiye--turkce-yapay-zeka-kaynaklari":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",160015,2,"2026-04-18T11:30:52",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":76,"owner_twitter":76,"owner_website":78,"owner_url":79,"languages":76,"stars":80,"forks":81,"last_commit_at":82,"license":83,"difficulty_score":84,"env_os":85,"env_gpu":86,"env_ram":86,"env_deps":87,"category_tags":90,"github_topics":91,"view_count":32,"oss_zip_url":76,"oss_zip_packed_at":76,"status":17,"created_at":104,"updated_at":105,"faqs":106,"releases":107},9301,"deeplearningturkiye\u002Fturkce-yapay-zeka-kaynaklari","turkce-yapay-zeka-kaynaklari","Türkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.","turkce-yapay-zeka-kaynaklari 是一个由\"Deep Learning Türkiye\"社区维护的开源知识库，旨在系统性地汇总土耳其本土在深度学习与机器学习领域的优质资源。它解决了土耳其语 AI 学习资源分散、难以查找的痛点，为母语使用者提供了一个集中的入口，涵盖从基础理论到前沿应用的全方位内容。\n\n该资源库非常适合希望使用土耳其语进行学习的开发者、数据科学家、研究人员以及高校学生。无论是初学者想要理解神经网络的基本概念，还是资深从业者寻找特定的算法实现、数据集或硬件部署方案，都能在此找到对应的博客文章、视频教程、科学论文、代码示例及书籍推荐。其内容结构清晰，划分为基础主题、算法、应用场景、框架、竞赛等多个板块，并持续收录来自社区贡献者的最新成果。\n\n作为区域性垂直领域的知识聚合平台，turkce-yapay-zeka-kaynaklari 的独特价值在于打破了语言壁垒，让非英语背景的爱好者也能无障碍地接触高质量的 AI 技术内容，有效促进了土耳其本地人工智能生态的交流与发展。","\nBu sayfada Türkiye'de derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) alanında yapılan çalışmaları (blog yazısı, video ders, bilimsel makale, kodlar, verisetleri) bulabilirsiniz. \n\nSayfa, **Deep Learning Türkiye** topluluğu tarafından desteklenmektedir. Derin öğrenme ve makine öğrenmesiyle ilgili **çalışmalarınız var ise** Deep Learning Türkiye topluluğuna katılmak için [başvuru formunu](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLScUmwLsWTl-Xj5E4Ble2jtaSlezZ_gklQNA2fylYQ7KGH4DNQ\u002Fviewform) doldurabilirsiniz.\n\nBizi [LinkedIn](http:\u002F\u002Flinkedin.com\u002Fcompany\u002Fdeep-learning-turkiye), [Facebook](https:\u002F\u002Fwww.facebook.com\u002Fdeeplearningtr\u002F) ve [Twitter](https:\u002F\u002Ftwitter.com\u002Fdeeplearningtr)'da takip edebilir, [Medium-Türkçe](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye) ve [Medium-İngilizce](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkey) platformunda da blog yazılarımızı okuyabilir, isterseniz katkı sağlayabilirsiniz:\n\nSayfaya yeni kaynak eklemek için: [Katkıda bulunma rehberi](contributing.md) adresindeki talimatları izleyin.\n\n\n## İçerikler\n\n* **[Temel Konular](#temel-konular)**  \n\n* **[Algoritmalar](#algorİtmalar)**  \n\n* **[Kullanım Alanları](#kullanim-alanlari)**  \n\n* **[Frameworks](#frameworks)**  \n\n* **[Donanım ve Bulut Destekleri](#donanim-ve-bulut-destekleri)**\n\n* **[Bilimsel Makaleler](#bİlİmsel-makaleler)**  \n\n* **[Verisetleri](#verİsetlerİ)**  \n\n* **[Video Dersler](#vİdeo-dersler)**  \n\n* **[Sunumlar](#sunumlar)**  \n\n* **[Github](#github)**  \n\n* **[Bloglar](#bloglar)**\n\n* **[Kitaplar](#kitaplar)**\n\n* **[Yarışmalar (Kaggle vb.)](#yarışmalar)**\n\n* **[Mobil Uygulamalar](#mobil-uygulamalar)**\n\n## TEMEL KONULAR\n* [Temel: Şu Kara Kutuyu Açalım: Yapay Sinir Ağları](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002F%C5%9Fu-kara-kutuyu-a%C3%A7alim-yapay-sinir-a%C4%9Flar%C4%B1-7b65c6a5264a) (Merve Ayyüce Kızrak)\n* [Motivasyon: Yapay Zeka ve Derin Öğrenmenin Hikayesi](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fmotivasyon-yapay-zeka-ve-derin-%C3%B6%C4%9Frenme-48d09355388d) (Merve Ayyüce Kızrak)\n* [Derin Öğrenme Başlangıç Seti - Donanım Ve Yazılım](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F10\u002Fderin-ogrenme-baslangic-seti.html) (Arda Mavi)\n* [Yapay Zeka - Düşünen Ve Üreten Makinelerin Doğuşu](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F09\u002Fyapay-zekanin-gelecegi.html) (Arda Mavi)\n* [İnsanda Ve Makinede Öğrenme](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Finsanda-ve-makinede-ogrenme.html) (Arda Mavi)\n* [Bilgisayarda Görüntü Ve Sayı Dizileri](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fbilgisyarda-goruntu-ve-sayi-dizileri.html) (Arda Mavi)\n* [Derin Öğrenme 1](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F10\u002Fderin-ogrenme-1.html) (Birol Kuyumcu)\n* [Derin Öğrenme 2](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F11\u002Fderin-ogrenme-2.html) (Birol Kuyumcu)\n* [Derin Öğrenme 3](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F11\u002Fderin-ogrenme-3.html) (Birol Kuyumcu)\n* [Derin Öğrenme , Yapay Zeka ve Bilgisayar Bilim](http:\u002F\u002Fsayilarvekuramlar.blogspot.com\u002F2015\u002F12\u002Fbilgisayar-bilim-yapay-zeka.html) (Burak Bayramlı)\n* [Makine Öğrenimi Eğlencelidir](https:\u002F\u002Fmedium.com\u002Ft%C3%BCrkiye\u002Fmakine-%C3%B6%C4%9Frenimi-e%C4%9Flencelidir-2ad33ae37bea)(Özgür Şahin)\n* [Makine Öğrenimi Eğlencelidir 2](https:\u002F\u002Fmedium.com\u002Fbili%C5%9Fim-hareketi\u002Fmakine-%C3%B6%C4%9Frenimi-e%C4%9Flencelidir-2-k%C4%B1s%C4%B1m-6b464cbdf40c)(Atakan Yenel)\n* [Makine Öğrenmesi Nedir?](https:\u002F\u002Fmedium.com\u002Ftürkiye\u002Fmakine-öğrenmesi-nedir-20dee450b56e) (Halil İbrahim Şafak)\n* [Makine Öğrenmesi 101](https:\u002F\u002Fveribilimcisi.com\u002Fmakine-ogrenmesi\u002F) (Seray Beşer)\n* [Derin Öğrenme 101](https:\u002F\u002Fveribilimcisi.com\u002Fderin-ogrenme-101\u002F) (Seray Beşer)\n* [Makine Öğrenmesi Matematiği](https:\u002F\u002Fveribilimcisi.com\u002Fmakine-ogrenmesi-matematigi\u002F) (Seray Beşer)\n* [Veri Bilimcisi Olma Rehberi](http:\u002F\u002Fbilisim.io\u002F2017\u002F09\u002F28\u002Fveri-bilimcisi-olma-rehberi\u002F) (Şefik İlkin Serengil)\n* [Python: Sıfırdan Uzmanlığa Programlama ](https:\u002F\u002Fwww.udemy.com\u002Fpython-sfrdan-uzmanlga-programlama-1\u002F) (Kaan Can Yılmaz)\n* [Data Science ve Python](https:\u002F\u002Fwww.udemy.com\u002Fdata-science-sfrdan-uzmanlga-veri-bilimi-2\u002F) (Kaan Can Yılmaz)\n* [Data Visualization](https:\u002F\u002Fwww.udemy.com\u002Fdata-visualization-adan-zye-veri-gorsellestirme-3\u002F) (Kaan Can Yılmaz)\n* [Makine Öğrenmesi](https:\u002F\u002Fwww.udemy.com\u002Fmachine-learning-ve-python-adan-zye-makine-ogrenmesi-4\u002F) (Kaan Can Yılmaz)\n\n## ALGORİTMALAR\n\n### Algoritmalar için Püf Noktaları\n* [Derin Öğrenme Uygulamalarında En Sık kullanılan Hiper-parametreler](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fderin-ogrenme-uygulamalarinda-en-sik-kullanilan-hiper-parametreler-ece8e9125c4) (Necmettin Çarkacı)\n* [Derin Öğrenme Uygulamalarında Başarım İyileştirme (Regularization) Yöntemleri](https:\u002F\u002Fmedium.com\u002F@necmettin.carkaci\u002Fderin-öğrenme-uygulamalarında-başarım-iyileştirme-yöntemleri-regularization-fb521e64c30f) (Necmettin Çarkacı)\n\n\n### Yapay Sinir Ağları (Artificial Neural Networks)\n* [Yapay Sinir Ağlarına Giriş](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fsinir-aglari.html) (Arda Mavi)\n* [Yapay Sinir Ağları](http:\u002F\u002Fwww.akanesen.com\u002F2017\u002F09\u002Fyapay-sinir-aglar.html) (Birol Akan Esen)\n* [Yapay Sinir Ağları Temel Kavramlar: Perceptron, Skor fonksiyonu ve Hata hesaplaması(loss function)](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fderin-öğrenme-uygulamalarında-temel-kavramlar-skor-ve-çarkacı\u002F) (Necmettin Çarkacı)\n* [Nöral Ağlar: Geçmiş Hatalardan Dersler Çıkarmak](http:\u002F\u002Fbilisim.io\u002F2017\u002F07\u002F08\u002Fnoral-aglar-gecmis-hatalardan-dersler-cikarmak\u002F) (Şefik İlkin Serengil)\n* [Nöral Ağlar Öğrenme Algoritması Anlama Kılavuzu: Geri Yayılım Algoritması](http:\u002F\u002Fbilisim.io\u002F2017\u002F07\u002F11\u002Fnoral-aglar-ogrenme-algoritmasi-anlama-kilavuzu-geri-yayilim-algoritmasi\u002F) (Şefik İlkin Serengil)\n* [Yapay Sinir Ağları (Neural Network)](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F08\u002F13\u002Fyapay-sinir-aglari\u002F) (Seray Beşer)\n* [Algılayıcı (Perceptron (P))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F08\u002F13\u002Fyapay-sinir-aglari\u002F#PERCEPTRON%20-%20ALGILAYICI) (Seray Beşer)\n* [İleri Beslemeli (Feed Forward (FF))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fileri-beslemeli-sinir-aglari-feedforward-neural-network\u002F) (Seray Beşer)\n* [Tekrarlayan Sinir Ağı (Recurrent Neural Network (RNN))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Ftekrarlayan-sinir-aglari-recurrent-neural-network\u002F) (Seray Beşer)\n* [Derin İleri Beslemeli (Deep Feed Forward (DFF))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fderin-ileri-beslemeli-sinir-aglari-deep-feedforward-network\u002F) (Seray Beşer)\n* [Uzun \u002F Kısa Süreli Bellek (Long \u002F Short Term Memory (LSTM))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fuzun-kisa-sureli-bellek-long-short-term-memory\u002F) (Seray Beşer)\n* [Yarıçapsal Temelli Ağ (Radial Basis Network (RBF))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fyaricapsal-temelli-ag-radial-basis-network\u002F) (Seray Beşer)\n* [Kapılı Tekrarlayan Hücre (Gated Recurrent Unit (GRU))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkapili-tekrarlayan-hucre-gated-recurrent-unit\u002F) (Seray Beşer)\n* [Otomatik Kodlayıcı (Auto Encoder (AE))](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fotomatik-kodlayici-auto-encoder\u002F) (Seray Beşer)\n* [Varyasyonel Otomatik Kodlayıcı (Variational AE (VAE))](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fvaryasyonel-otomatik-kodlayici-variational-autoencoder\u002F) (Seray Beşer)\n* [Gürültü Giderici Otomatik Kodlayıcı (Denoising AE (DAE))](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fgurultu-giderici-otomatik-kodlayici-denoising-autoencoder\u002F) (Seray Beşer)\n* [Seyrek Otomatik Kodlayıcı (Sparse AE (SAE))](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fseyrek-otomatik-kodlayici-sparse-autoencoder\u002F) (Seray Beşer)\n* [Markov Zinciri (Markov Chain (MC))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fmarkov-zinciri-markov-chain\u002F) (Seray Beşer)\n* [Hopfield Ağı (Hopfield Network (HN))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fhopfield-agi-hopfield-network\u002F) (Seray Beşer)\n* [Boltzmann Makinesi (Boltzmann Machine (BM))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fboltzmann-makinesi-boltzmann-machine\u002F) (Seray Beşer)\n* [Kısıtlı Boltzmann Makinesi (Restricted BM (RBM))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkisitli-boltzmann-makinesi-restricted-boltzmann-machine-rbm\u002F) (Seray Beşer)\n* [Derin İnanç Ağı (Deep Belief Network (DBN))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fderin-inanc-agi-deep-belief-network\u002F) (Seray Beşer)\n* [Konvolüsyonel Sinir Ağı (Convolutional Neural Network (CNN))](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkonvolusyonel-sinir-agi-convolutional-neural-network\u002F) (Seray Beşer)\n\n### Evrişimli Sinir Ağları (Convolutional Neural Networks)\n* [Derin Bir Karşılaştırma: Inception ve Res-Net Verisyonları](http:\u002F\u002Fwww.ayyucekizrak.com\u002Fblogdetay\u002Fyapay-zeka-ve-derin-ogrenme-yazi-dizisi\u002Fderin-bir-karsilastirma-inception-ve-res-net-versiyonlari) (Bağlantı güncellenecek!) (Merve Ayyüce Kızrak)\n* [Derine Daha Derine: Evrişimli Sinir Ağları](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fderi%CC%87ne-daha-deri%CC%87ne-evri%C5%9Fimli-sinir-a%C4%9Flar%C4%B1-2813a2c8b2a9) (Merve Ayyüce Kızrak)\n* [Evrişimli Sinir Ağlarına Giriş](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fconvolutional-networks.html) (Arda Mavi)\n* [Tensorflow Tabanlı Keras ile MNIST Veriseti Üzerinde Çalışma](http:\u002F\u002Ferdoganb.com\u002F2017\u002F04\u002Fkerastensorflow-ile-rakamlari-tanima-mnist-dataset\u002F) (Erdoğan Bavaş)\n* [Konvolüsyonel Nöral Ağlara Kısa Bir Giriş](http:\u002F\u002Fbilisim.io\u002F2018\u002F01\u002F07\u002Fkonvolusyonel-noral-aglara-kisa-bir-giris\u002F) (Şefik İlkin Serengil)\n* [Öğrenim Transferi: Keras ile Inception V3 kullanımı](http:\u002F\u002Fbilisim.io\u002F2018\u002F01\u002F22\u002Fogrenim-transferi-keras-ile-inception-v3-kullanimi\u002F) (Şefik İlkin Serengil)\n\n### Kapsül Ağları (Capsule Networks)\n* [Yapay Zekada Büyük Yenilik: Kapsül Ağları (Capsule Networks)](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fyapay-zekan%C4%B1n-yeni-ve-%C3%A7ekici-mimarisi-kaps%C3%BCl-a%C4%9F%C4%B1na-uygulamal%C4%B1-bir-bak%C4%B1%C5%9F-ef7310e3d847) (Merve Ayyüce Kızrak)\n\n### Çekişmeli Üretici Ağlar (Generative Adversarial Networks)\n* [Generative Adversarial Networks — GAN nedir ? ( Türkçe )](https:\u002F\u002Fmedium.com\u002F@mubuyuk51\u002Fgenerative-adversarial-networks-gan-nedir-t%C3%BCrk%C3%A7e-5819fe9c1fa7) (Muhammed Buyukkınacı)\n\n### Otokodlayıcılar (Autoencoders)\n* [Yapay Nöral Ağlar: Autoencoder'lar](https:\u002F\u002Fwww.farukeroglu.org\u002F2018\u002F06\u002Fyapay-noral-aglar-autoencoder.html) (Faruk Eroğlu)\n* [Otomatik Kodlayıcı (Autoencoder)](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fotomatik-kodlayici-auto-encoder\u002F) (Seray Beşer)\n* [Gürültü Giderici Otomatik Kodlayıcı (Denoising Autoencoder)](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fgurultu-giderici-otomatik-kodlayici-denoising-autoencoder\u002F) (Seray Beşer)\n* [Seyrek Otomatik Kodlayıcı (Sparse Autoencoder)](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fseyrek-otomatik-kodlayici-sparse-autoencoder\u002F) (Seray Beşer)\n* [Varyasyonel Otomatik Kodlayıcı (Variational Autoencoder)](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fvaryasyonel-otomatik-kodlayici-variational-autoencoder\u002F) (Seray Beşer)\n\n\n\n## KULLANIM ALANLARI\n### Doğal Dil İşleme (Natural Language Processing)\n* [Keras ile Duygu Analizi](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F10\u002Fkeras-ile-duygu-analizi.html) (Birol Kuyumcu)\n* [Türkçe Metin İşlemede İlk Adımlar](http:\u002F\u002Fwww.veridefteri.com\u002F2017\u002F11\u002F20\u002Fturkce-metin-islemede-ilk-adimlar\u002F) (İlker Birbil)\n\n### Siber Güvenlik (Cyber Security)\n* [Derin Ögrenme Teknolojileri Kullanarak Dağıtık Hizmet Dışı Bırakma Saldırılarının Tespit Edilmesi\n](https:\u002F\u002Focatak.github.io\u002Fpapers\u002Fposter_foc.pdf) (Ferhat Özgür Çatak, Ahmet Fatih Mustaçoglu)\n\n### Bilgisayarlı Görü (Computer Vision)\n* [Optik Karakter Tanıma, Yazı Tanıma (Optical Character Recognition -OCR-)](https:\u002F\u002Fburakbayramli.github.io\u002Fdersblog\u002Falgs\u002Focr\u002Foptik_karakter_tanima_yazi_tanima__optical_character_recognition_ocr_.html) (Burak Bayramlı)\n* [YOLO: Gerçek Zamanlı Nesne Tespiti Kütüphanesi (Darknet) Kurulumu](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fgercek-zamanli-nesne-tespiti-kutuphanesi-darknet-kurulumu) (Yavuz Kömeçoğlu)\n* [YOLO'da Kendi Özel Kişi yada Nesnemizin Algılanmasını Nasıl Sağlarız?](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fyolo-da-kendi-ozel-nesnemizin-algilanmasini-nasil-saglariz) (Yavuz Kömeçoğlu)\n* [Görüntü Tanıyan Mobil Uygulama Nasıl Geliştirilir?](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fg%C3%B6r%C3%BCnt%C3%BC-tan%C4%B1yan-mobil-uygulama-nas%C4%B1l-geli%C5%9Ftirilir-33760f7d827) (Özgür Şahin)\n* [10 Dakikada Görüntü Sınıflandıran Mobil Uygulama Geliştirin](https:\u002F\u002Fmedium.com\u002Fnsistanbul\u002F10-dakikada-g%C3%B6r%C3%BCnt%C3%BC-s%C4%B1n%C4%B1fland%C4%B1ran-mobil-uygulama-geli%C5%9Ftirin-7567371839b0) (Özgür Şahin)\n\n## FRAMEWORKS\n### Caffe\n* [Caffe Kılavuzu - Tüm detaylarıyla Caffe ile çalışma rehberi](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Fcaffe-klavuzu) (Birol Kuyumcu)\n* [Pratik Caffe Kullanımı](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Fpratik-caffe) (Birol Kuyumcu)\n* [Caffe Fine Tuning: Caffe'yi Kendi Verisetiniz ile Kullanma](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fcaffe-fine-tuning) (Yavuz Kömeçoğlu)\n* [Windows İşletim Sistemi için Caffe Kurulumu](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fwindows-icin-caffe-kurulumu.html) (Mesut Pişkin)\n\n### Keras\n* [Keras'a Giriş-1](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F01\u002Fkeras-giris-1.html) (Birol Kuyumcu)\n* [Keras'a Giriş-2 ( LSTM )](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F03\u002Fkerasa-giris-2-lstm.html) (Birol Kuyumcu)\n* [Keras Türkçe Dokümantasyon](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fkeras_turkish_doc) (Kemalcan Bora)\n* [Keras Kurulumu](http:\u002F\u002Fibrahimdelibasoglu.blogspot.com.tr\u002F2017\u002F08\u002Fpython-tensorflow-ile-keras-derin.html) (İbrahim Delibaşoğlu)\n* [Keras ile Sonar Verisi Sınıflandırma](http:\u002F\u002Fibrahimdelibasoglu.blogspot.com.tr\u002F2017\u002F09\u002Fkeras-ile-derin-ogrenmeye-giris-snflama.html) (İbrahim Delibaşoğlu)\n\n\n### TensorFlow\n* [TensorFlow ile Derin Öğrenmeye Giriş](https:\u002F\u002Femredurukn.github.io\u002F2016\u002F11\u002F02\u002Ftensorflow-ile-derin-ogrenmeye-giris.html) (Emre Durukan)\n* [Tensorflow'u Anlamak](https:\u002F\u002Fmcemilg.github.io\u002Fgeneral\u002F2017\u002F11\u002F23\u002Ftensorflow\u002F) (M.Cemil Güney)\n* [Tensorflow Türkçe Eğitim Dökümanları](https:\u002F\u002Fgithub.com\u002FAelvangunduz\u002Ftensorflow_tutorials) (Ayse Elvan Aydemir)\n* [Tensorflow 101](https:\u002F\u002Fveribilimcisi.com\u002Ftensorflow-101\u002F) (Seray Beşer)\n\n\n### PyTorch\n* [PyTorch ile Derin Öğrenmeye Giriş: Kurulum](https:\u002F\u002Fmedium.com\u002F@ozgungenc\u002Fpytorch-ile-derin-%C3%B6%C4%9Frenmeye-giri%C5%9F-kurulum-2194a06ce0c) (Özgün Genç)\n\n### Deeplearning4j\n* [Deeplearning4j ile Derin Öğrenmeye Giriş](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fdeeplearning4j-ile-derin-ogrenmeye-giris.html) (Mesut Pişkin)\n* [Deeplearning4j Mimarisi](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fdeeplearning4j-mimarisi-ve-kurulum.html) (Mesut Pişkin)\n* [Deeplearning4j ile Yapay Sinir Ağları](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fyapay-sinir-agi-derin-ogrenme.html) (Mesut Pişkin)\n\n### FANN\n* [FANN Tool Kılavuzu](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Ffann-tool-klavuzu) (Birol Kuyumcu)\n\n## DONANIM VE BULUT DESTEKLERİ\n\n### Donanım\n\n#### NVIDIA Titan Serisi\n\n#### NVIDIA Jetson TX Serisi\n\n#### Intel-Movidius Neural Compute Stick\n* [INTEL-Movidius Neural Compute Stick Nedir ve Nasıl Kullanılır](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fintel-movidius-neural-compute-stick-nedir-ve-nas%C4%B1l-kullan%C4%B1l%C4%B1r-85fc9af6dc26) (Merve Ayyüce Kızrak)\n* [Raspberry Pi 3 üzerinde Intel Movidius Neural Compute Stick ile Derin Öğrenme Uygulamaları Çalıştırma](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fraspberry-pi-3-uzerinde-intel-movidius-neural-compute-stick-ile-derin-ogrenme-uygulamalari-calistirma) (Yavuz Kömeçoğlu)\n\n### Bulut\n\n#### Google  Colaboratory \n* [Google Colab ile Ücretsiz GPU Kullanımı](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fgoogle-colab-ile-%C3%BCcretsiz-gpu-kullan%C4%B1m%C4%B1-30fdb7dd822e) (Fuat)\n### Derin öğrenme için sistem hazırlama ve Kurulum rehberleri\n#### Ekran kartı sürücüsü, Cuda ve Cudnn Kurulumu\n* [NVIDIA GPU Sürücüsü, CUDA ve cudNN Kurulum Rehberi](https:\u002F\u002Fgithub.com\u002Fearcz\u002FNVIDIA-GPU-Surucusu-ve-CUDA-Yukleme) (Ender Ayhan Rencüzoğulları)\n\n#### Microsoft Azure Notebook\n\n## BİLİMSEL MAKALELER\n### Genel (Review\u002FSurvey)\n* [Derin Öğrenme Yöntemleri ve Uygulamaları Hakkında Bir İnceleme](http:\u002F\u002Fdergipark.gov.tr\u002Fdownload\u002Farticle-file\u002F394923) (Abdulkadir Şeker, Banu Diri, Hasan Hüseyin Balık )\n\n### Bilgisayarlı Görü (Computer Vision)\n* [MARVEL: A Large-Scale Image Dataset for Maritime Vessels](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-54193-8_11) (Erhan Gündoğdu, Berkan Solmaz, Veysel Yücesoy, Aykut Koç)\n* [Face Recognition Classifier Based on Dimension Reduction in Deep Learning Properties](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7960368\u002F) (Ahmet Bilgiç, Onur Can Kurban, Tülay Yıldırım)\n* [Signature recognition application based on deep learning](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960454\u002F) (Nurullah Çalık, \nOnur Can Kurban, Ali Rıza Yılmaz, Lütfiye Durak Ata, Tülay Yıldırım)\n* [On identifying leaves: A comparison of CNN with classical ML methods](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960257\u002F) (Mohamed Abbas Hedjazi, Ikram Kourbane, Yakup Genç)\n* [On identifying leaves: A comparison of CNN with classical ML methods](https:\u002F\u002Fweb.cs.hacettepe.edu.tr\u002F~aykut\u002Fpapers\u002Fieee-tmm17.pdf) (Çağdaş Bak, Aysun Koçak, Erkut Erdem, Aykut Erdem)\n* [Exploiting Convolution Filter Patterns for Transfer Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06973) (Mehmet Aygün, Yusuf Aytar, Hazım Kemal Ekenel)\n* [The Unconstrained Ear Recognition Challenge](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06997) (Žiga Emeršič, Dejan Štepec, Vitomir Štruc, Peter Peer, Anjith George, Adil Ahmad, Elshibani Omar, Terrance E. Boult, Reza Safdari, Yuxiang Zhou, Stefanos Zafeiriou, Dogucan Yaman, Fevziye I. Eyiokur, Hazim K. Ekenel)\n* [Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection](https:\u002F\u002Farxiv.org\u002Fabs\u002F1710.06160) (Damien Matti, Hazım Kemal Ekenel, Jean-Philippe Thiran)\n* [Combining Multiple Views for Visual Speech Recognition](http:\u002F\u002Favsp2017.loria.fr\u002Fwp-content\u002Fuploads\u002F2017\u002F07\u002FAVSP2017_paper_25.pdf) (Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazım Kemal Ekenel, Jean-Philippe Thiran)\n* [A Computer Vision System to Localize and Classify Wastes on the Streets](https:\u002F\u002Finfoscience.epfl.ch\u002Frecord\u002F231365\u002Ffiles\u002FA-Computer-Vision-System%20to-Localize-and-Classify-Wastes-on-the-Streets.pdf) (Mohammad Saeed Rad,Andreas von Kaenel, Andre Droux, Francois\nTieche, Nabil Ouerhani, Hazım Kemal Ekenel, Jean-Philippe Thiran)\n\n### Türkçe Doğal Dil İşleme\n* [Linguistic Features in Turkish Word Representations](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960223\u002F) (Onur Güngör, Eray Yıldız)\n* [Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.00506) (Onur Güngör, Eray Yıldız, Suzan Üsküdarlı, Tunga Güngör)\n* [Zemberek Parser for python3.x](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fzemberek_parser)  (Kemalcan Bora)\n* [A Morphology-Aware Network for Morphological Disambiguation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.03654.pdf) (Eray Yıldız, Çağlar Tırkaz, H. Bahadır Şahin, Mustafa Tolga Eren, Ozan Sönmez)\n* [Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.02363.pdf) (H. Bahadır Şahin, Çağlar Tırkaz, Eray Yıldız, Mustafa Tolga Eren, Ozan Sönmez)\n* [Türkçe ve Doğal Dil İşleme](http:\u002F\u002Fdergipark.gov.tr\u002Fdownload\u002Farticle-file\u002F207207) (Kemal Oflazer)\n* [Turkish and its challenges for language processing](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10579-014-9267-2) (Kemal Oflazer)\n* [Zemberek Docker REST Sunucusu](https:\u002F\u002Fgithub.com\u002Fcbilgili\u002Fzemberek-nlp-server) (Canbey Bilgili)\n\n### Ses İşleme\n* [A musical information retrieval system for Classical Turkish Music makams\n](http:\u002F\u002Fjournals.sagepub.com\u002Fdoi\u002Fabs\u002F10.1177\u002F0037549717708615?journalCode=simb) (Merve Ayyüce Kızrak, Bülent Bolat)\n\n### Tahmin\n* [Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations](http:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0950705117304252) (Hakan Gündüz, Yusuf Yaslan, Zehra Çataltepe)\n\n### Siber Güvenlik\n* [Derin Ögrenme Teknolojileri Kullanarak Dağıtık Hizmet Dışı Bırakma Saldırılarının Tespit Edilmesi\n](https:\u002F\u002Focatak.github.io\u002Fpapers\u002Fposter_foc.pdf) (Ferhat Özgür Çatak, Ahmet Fatih Mustaçoglu)\n* [CPP-ELM: Cryptographically Privacy-Preserving Extreme Learning Machine for Cloud Systems](http:\u002F\u002Fwww.atlantis-press.com\u002Fjournals\u002Fijcis\u002F25885040) (Ferhat Özgür Çatak, Ahmet Fatih Mustaçoglu)\n\n## VERİSETLERİ\n* [İşaret Dili İle Rakamlar Veriseti](https:\u002F\u002Fgithub.com\u002Fardamavi\u002FSign-Language-Digits-Dataset) (Türkiye Ankara Ayrancı Anadolu Lisesi - Zeynep Dikle & Arda Mavi)\n* [Marvel: A Large-Scale Image Dataset for Maritime Vessels](https:\u002F\u002Fgithub.com\u002Favaapm\u002Fmarveldataset2016) (Erhan Gündoğdu, Berkan Solmaz, Veysel Yücesoy, Aykut Koç)\n* [Yıldız Teknik Üniversitesi Kemik Doğal Dil İşleme Grubu Verisetleri](http:\u002F\u002Fwww.kemik.yildiz.edu.tr\u002F?id=28) (YTÜ Kemik Doğal Dil İşleme Grubu)\n* [TTC-3600: A new benchmark dataset for Turkish text categorization] (https:\u002F\u002Fgithub.com\u002Fdenopas\u002FTTC-3600) (Deniz Kılınç, Akın Özçift, Fatma Bozyigit, Pelin Yıldırım, Fatih Yücalar, Emin Borandag)\n* [Turkish Sentiment Dataset](http:\u002F\u002Fwww.baskent.edu.tr\u002F~msert\u002Fresearch\u002Fdatasets\u002FSentimentDatasetTR.html) (Ahmet Hayran, Mustafa Sert)\n* [English\u002FTurkish Wikipedia Named-Entity Recognition and Text Categorization Dataset](https:\u002F\u002Fdata.mendeley.com\u002Fdatasets\u002Fcdcztymf4k\u002F1) (H. Bahadır Şahin, Çağlar Tırkaz, Eray Yıldız, Mustafa Tolga Eren, Ozan Sönmez)\n* [Turkish NLP Dataset](https:\u002F\u002Ftscorpus.com)(Sezer, B., Sezer, T. 2013. TS Corpus: Herkes İçin Türkçe Derlem. Proceedings 27th National Linguistics Conference. May, 3-4 Mayıs 2013. Antalya, Kemer: Hacettepe University, English Linguistics Department. pp: 217-225)\n* [1B Tokens Turkish Corpus and Turkish word vectors and analogical reasoning task pairs](https:\u002F\u002Fgithub.com\u002Fonurgu\u002Flinguistic-features-in-turkish-word-representations\u002Freleases)(Onur Gungor, Eray Yildiz, \"Linguistic Features in Turkish Word Representations\", SIU, Antalya, 2017)\n* [Turkish Language Resources compiled by Deniz Yüret](http:\u002F\u002Fwww.denizyuret.com\u002F2006\u002F11\u002Fturkish-resources.html)\n* [METU-Sabanci Turkish treebank](https:\u002F\u002Fweb.itu.edu.tr\u002Fgulsenc\u002Ftreebanks.html)\n* [SemEval-2016 ABSA Telecom Tweets-Turkish: Test Data-Phase A (Subtask 1)](http:\u002F\u002Fmetashare.ilsp.gr:8080\u002Frepository\u002Fbrowse\u002Fsemeval-2016-absa-telecom-tweets-turkish-test-data-phase-a-subtask-1\u002F5343e408ba0811e5ab4f842b2b6a04d71f53ece5fa7a4dd286e99e539ac3e27f\u002F)\n* [SemEval-2016 ABSA Restaurant Reviews-Turkish: Train Data (Subtask 1)](http:\u002F\u002Fmetashare.ilsp.gr:8080\u002Frepository\u002Fbrowse\u002Fsemeval-2016-absa-restaurant-reviews-turkish-train-data-subtask-1\u002Fff5dad70676311e5bf9c842b2b6a04d71fa7fa3ba4504a228dafe0c24560585b\u002F)\n* [Turkish Paraphrase Corpus (TuPC)](https:\u002F\u002Fosf.io\u002Fwp83a\u002F)(Eyecioglu, Asli, and Bill Keller. \"ASOBEK at SemEval-2016 Task 1: Sentence Representation with Character N-gram Embeddings for Semantic Textual Similarity.\" SemEval@ NAACL-HLT. 2016.)\n* [Turkish WordNet (KeNet)](http:\u002F\u002Fhaydut.isikun.edu.tr\u002Fkenet.html)(Sasmaz, E., R. Ehsani, O. T. Yildiz, \"Hypernym extraction from Wikipedia and Wiktionary\", SIU, Antalya, Turkey, 2017)\n* [Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002FParkinson%2BSpeech%2BDataset%2Bwith%2B%2BMultiple%2BTypes%2Bof%2BSound%2BRecordings#)(Erdogdu Sakar, B., Isenkul, M., Sakar, C.O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., Kursun, O., 'Collection and Analysis of a Parkinson Speech Dataset with Multiple Types of Sound Recordings', IEEE Journal of Biomedical and Health Informatics, vol. 17(4), pp. 828-834, 2013.)\n* [Turkiye Student Evaluation Data Set](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fturkiye+student+evaluation#)(Gunduz, G. & Fokoue, E. (2013).)\n* [Combined Cycle Power Plant Data Set](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fcombined+cycle+power+plant)(Pınar Tüfekci, Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods, International Journal of Electrical Power & Energy Systems, Volume 60, September 2014, Pages 126-140, ISSN 0142-06)\n* [Dermatology Data Set](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fdermatology)(G. Demiroz, H. A. Govenir, and N. Ilter, \"Learning Differential Diagnosis of Eryhemato-Squamous Diseases using Voting Feature Intervals\", Aritificial Intelligence in Medicine, 1998-2004)\n* [Arrhythmia Data Set](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Farrhythmia)(H. Altay Guvenir, Burak Acar, Gulsen Demiroz, Ayhan Cekin \"A Supervised Machine Learning Algorithm for Arrhythmia Analysis.\" Proceedings of the Computers in Cardiology Conference, Lund, Sweden, 1997.)\n* [Artificial Characters Data Set](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002FArtificial+Characters)( H. Altay Guvenir et al, 1992)\n* [Turkish Natural Language Processing Toolkit- embedded in Zemberek](http:\u002F\u002Fwww.aliok.com.tr\u002Fprojects\u002F2014-10-02-trnltk.html)\n* [235.000 Turkish Product Reviews](https:\u002F\u002Fgithub.com\u002Ffthbrmnby\u002Fturkish-text-data)\n* [ODP TR-30 Turkish Search Result Clustering Dataset](https:\u002F\u002Fgithub.com\u002Ffaraday\u002Fodp-tr30) (Ç. Çallı, 2010)\n* [Modacruz ve Zara'da bulunan kıyafetlerin dataseti ](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fflora_fashion_scraping) (Kemalcan Bora)\n## VİDEO DERSLER\n### Genel\n* [Ankara Deep Learning - Derin Öğrenme Etkinliği 1](https:\u002F\u002Fyoutu.be\u002FK74rzKSsGs8) (Ferhat Kurt) {96 dakika}\n* [ODTÜ Görüntü Analizi Uygulama ve Araştırma Merkezi (OGAM) Yaz Okulu 2016](http:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fvideolar) (ODTÜ)\n\n### Yapay Sinir Ağları\n* [Neural Network 1 : Eğitime ve Kavramlara Giriş](https:\u002F\u002Fyoutu.be\u002FB5MmXmMMuvI) (Dr. Sadi Evren SEKER @BilgisayarKavramlari) {23 dakika}\n* [Neural Network 2: Perceptron Kavramı ve Öğrenme](https:\u002F\u002Fyoutu.be\u002F5Lo_HUDtxtw) (Dr. Sadi Evren SEKER @BilgisayarKavramlari) {13 dakika}\n* [Neural Network 3: Çok Katmanlı Yapay Sinir Ağları](https:\u002F\u002Fyoutu.be\u002FqrmaixHBrzU) (Dr. Sadi Evren SEKER @BilgisayarKavramlari) {13 dakika}\n* [Yapay Sinir Ağlarının Matematiği ve 18 Satırda Matematik Olarak Kodlanması](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=icrcbqPNrNE\u002F) (Mehmet Burak Sayıcı)\n\n### Yapay Zeka\n* [Yapay Zeka (Artificial Intelligence) - Oynatma Listesi](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLh9ECzBB8tJOtaD6DFxqRdP7QHIaBFcbW) (Dr. Sadi Evren SEKER @BilgisayarKavramlari) {48 Video}\n* [Yapay Zeka ve Deep Learning](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qk1RjRLIAq4) (Merve Ayyüce Kızrak) {68 dakika}\n* [Yapay Zeka Çağı | TEDxMETUAnkara](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=d4kQVyAEsqA) (Dr. Şeyda Ertekin) {18 dakika}\n\n### Bilgisayarlı Görü\n* [Uzaktan Algılanmış Görüntülerin Piksel Düzeyinde Sınıflandırılması Bölüm 1\u002F2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Y087JVjzw-Y) (Erhan Abdullah (Erchan Aptoula) @Data İstanbul) {60 dakika}\n* [Uzaktan Algılanmış Görüntülerin Piksel Düzeyinde Sınıflandırılması Bölüm 2\u002F2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EAYNMnMBqnA) (Erhan Abdullah (Erchan Aptoula) @Data İstanbul) {30 dakika}\n* [Derin Öğrenmeye Derinlemesine Dalış](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zJPW6Lyf_Xs) (Şefik İlkin Serengil @Softtech Sahnesi) {52 dakika}\n* [Makine Öğrenmesi Çağında Hayatta Kalma Rehberi](https:\u002F\u002Fyoutu.be\u002FP2MwuGpRgSQ) (Şefik İlkin Serengil @İstanbul Coding Talks) {84 dakika}\n* [Derin Öğrenme: Dünü, Bugünü, Yarını](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ITCD2Z4jT8w) (Şefik İlkin Serengil @Bilgisayar Mühendisleri Odası) {100 dakika}\n* [Keras ile Convolutional Neural Networks ](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e\u002F) (Mehmet Burak Sayıcı)\n* [Keras ile Convolutional Neural Networks ](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e\u002F) (Mehmet Burak Sayıcı)\n\n### IoT\n* [IoT ve Derin Öğrenme Etkinliği](https:\u002F\u002Fyoutu.be\u002Ffqf6m3R4psQ) (Ferhat Kurt) {82 dakika}\n\n## Framework\n### Keras\n* [Keras Video Eğitim Serisi](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e) (Mehmet Burak Sayıcı) {21 video, artmakta}\n\n### Julia\n* [Julia ve Knet ile Derin Öğrenmeye Giriş](https:\u002F\u002Fyoutu.be\u002F3TR3Rx-Esis) (Doç. Dr. Deniz Yuret) {104 dakika}\n\n### MatConvNet\n* [MatConvNet ve Matlab ile Derin Öğrenmeye Giriş](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nRVQQNw4Kh4&t=8s) (Ahmet Gökhan POYRAZ) {5 Video, eklemeler yapılacaktır}\n\n## Sunumlar\n* [Bozkırda Yapay Öğrenme Yaz Okulu 2017 - Sunumları](http:\u002F\u002Fgoo.gl\u002Fo2H9hA) (HUCVL)\n* [ODTü Görüntü Analizi Uygulama ve Araştırma Merkezi (OGAM) Yaz Okulu 2016 - Sunumları](https:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fsunumlar) (ODTÜ)\n* [ODTü Görüntü Analizi Uygulama ve Araştırma Merkezi (OGAM) Yaz Okulu 2016 - Videoları](http:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fvideolar) (ODTÜ)\n* [Deep Learning Türkiye - İstatistiksel Dil İşleme - Prof. Dr. Kemal Oflazer - Sunumları](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1w0L5r_C0BA1VLP8uA2iPNl90F8lXkMuc?usp=sharing) (DLTR)\n\n## Github\n### Doğal Dil İşleme\n* [Zemberek Parser for Python3](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fzemberek_parser)  (Kemalcan Bora)\n* [Turkish Word Embeddings with 900k data](https:\u002F\u002Fgithub.com\u002Fsavasy\u002FTurkishWordEmbeddings) (Savas Y)\n* [A finite-state morphological analyzer for Turkish](https:\u002F\u002Fgithub.com\u002Fcoltekin\u002FTRmorph) (Çağrı Çöltekin)\n* [Keras ile Türkçe Anlam Analizi(Olumlu - Olumsuz)](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTurkce-Anlam-Analizi) (Zeki Kuş)\n\n### Arama Algoritmaları\n* [C ile Ağaçlarda Bilgisiz\u002FBilmeden Arama Algoritmaları](https:\u002F\u002Fgithub.com\u002FEnes1313\u002FUninformed-Search-Strategies)  (Enes AYDIN)\n\n### Bilgisayarlı Görü\n* [CNN ile Görüntü Sınıflandırma](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FCaffeClassification) (Mesut Pişkin)\n* [Gerçek Zamanlı Cinsiyet Tespiti](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FGenderClassification) (Mesut Pişkin)\n* [Duygu-Duygu ve Cinsyet Tanıma](https:\u002F\u002Fgithub.com\u002Fayyucekizrak\u002FDuygu-Cinsiyet_Tanima-Emotion-Gender_Recognition) (Merve Ayyüce Kızrak-Yavuz Kömeçoğlu)\n* [CNN(Tensorflow) ile CIFAR10 Veri Setinin Sınıflandırılması ve Parametre Analizi](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTensorflow-CNN-with-CIFAR10-Dataset) (Zeki Kuş)\n* [CNN ile FashionMNIST Veri Setinin Sınıflandırılması](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTensorflow-CNN-with-FashionMNIST-Dataset) (Zeki Kuş)\n* [CNN(Keras) ile CIFAR10 Veri Setinin Sınıflandırılması](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FKeras-CNN-with-CIFAR10-Dataset) (Zeki Kuş)\n\n### Sinir Ağları\n* [Geri Beslemeli Yapay Sinir Ağı ile Karakter Tanıma](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FANNCharacterRecognition) (Mesut Pişkin)\n* [Cpp ile Yapay Sinir Ağları](https:\u002F\u002Fgithub.com\u002FEnes1313\u002FCpp-ile-YSA)  (Enes AYDIN)\n* [Makine Ogrenmesi](https:\u002F\u002Fgithub.com\u002FSerayBeser\u002FMakine-Ogrenmesi) (Seray Beşer)\n\n## Bloglar\n* [Deep Learning Türkiye Blog](http:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye)\n* [veridefteri.com](http:\u002F\u002Fveridefteri.com\u002F)\n* [zekimakine.com](http:\u002F\u002Fzekimakine.com\u002F)\n* [veribilimcisi.com](https:\u002F\u002Fveribilimcisi.com\u002F)\n* [alpslabel.wordpress.com](https:\u002F\u002Falpslabel.wordpress.com\u002F\u002F)\n* [makineogrenimi.wordpress.com](https:\u002F\u002Fmakineogrenimi.wordpress.com)\n* [devhunteryz.wordpress.com](https:\u002F\u002Fdevhunteryz.wordpress.com)\n\n## Kitaplar\n* [Yapay Öğrenme - Ethem Alpaydın](http:\u002F\u002Fwww.idefix.com\u002FKitap\u002FYapay-Ogrenme\u002FEthem-Alpaydin\u002FBilim\u002FPopuler-Bilim\u002Furunno=0000000362293)\n* [Derin Öğrenme - Ian Goodfellow, Yoshua Bengio, Aaron Courville](https:\u002F\u002Fwww.kitapyurdu.com\u002Fkitap\u002Fderin-ogrenme-ciltli\u002F480279.html)\n* [OpenCv Görüntü İşleme ve Yapay Öğrenme - Birol Kuyumcu](http:\u002F\u002Fwww.kitapyurdu.com\u002Fkitap\u002Fopencv-goruntu-isleme-ve-yapay-ogrenme\u002F376463.html)\n* [Yapay Zeka - Vasif Vagifoğlu Nabiyev](http:\u002F\u002Fwww.dr.com.tr\u002FKitap\u002FYapay-Zeka-Problemler-Yontemler-Algoritma-\u002FVasif-Vagifoglu-Nabiyev\u002FBilim\u002FPopuler-Bilim\u002Furunno=0000000435115)\n\n## Yarışmalar\n* [Kaggle Yarışma Deneyimim ve Gözlemlerim](https:\u002F\u002Fburakozdemir.co.uk\u002Farticle\u002Fkaggle-yarisma-deneyimim-ve-gozlemlerim) (Burak Özdemir)\n* [Kaggle BNP Paribas 93. Derece (Top %3) Yöntem ve Kod](https:\u002F\u002Fdatanoord.wordpress.com\u002F2016\u002F05\u002F05\u002Fkaggle-bnp-paribas-93-derece-top-3-yontem-ve-kod\u002F) (Ayşe Elvan Aldemir)\n\n## Mobil Uygulamalar\n* [Görme Engelliler için Para Okuyucu](https:\u002F\u002Fitunes.apple.com\u002Ftr\u002Fapp\u002Fpara-okuyucu\u002Fid1334298365?l=tr&mt=8) (Özgür Şahin)\n* [VisionDict](https:\u002F\u002Fitunes.apple.com\u002Ftr\u002Fapp\u002Fvisiondict\u002Fid1299943619?mt=8) (Kadir Mert Barutçuoğlu)\n","在本页面，您可以找到土耳其在深度学习和机器学习领域开展的研究工作（博客文章、视频课程、科学论文、代码、数据集等）。\n\n本页面由 **Deep Learning Türkiye** 社区支持。如果您也有与深度学习和机器学习相关的研究工作，欢迎填写 [申请表](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLScUmwLsWTl-Xj5E4Ble2jtaSlezZ_gklQNA2fylYQ7KGH4DNQ\u002Fviewform) 加入 Deep Learning Türkiye 社区。\n\n您还可以关注我们在 [LinkedIn](http:\u002F\u002Flinkedin.com\u002Fcompany\u002Fdeep-learning-turkiye)、[Facebook](https:\u002F\u002Fwww.facebook.com\u002Fdeeplearningtr\u002F) 和 [Twitter](https:\u002F\u002Ftwitter.com\u002Fdeeplearningtr\u002F) 上的账号，在 [Medium-土耳其语](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye) 和 [Medium-英语](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkey) 平台上阅读我们的博客文章，也欢迎您参与贡献：\n\n如需向本页面添加新资源，请按照 [贡献指南](contributing.md) 中的说明操作。\n\n\n## 内容\n\n* **[基础主题](#temel-konular)**  \n\n* **[算法](#algorİtmalar)**  \n\n* **[应用领域](#kullanim-alanlari)**  \n\n* **[框架](#frameworks)**  \n\n* **[硬件与云支持](#donanim-ve-bulut-destekleri)**\n\n* **[科学论文](#bİlİmsel-makaleler)**  \n\n* **[数据集](#verİsetlerİ)**  \n\n* **[视频课程](#vİdeo-dersler)**  \n\n* **[演示文稿](#sunumlar)**  \n\n* **[Github](#github)**  \n\n* **[博客](#bloglar)**\n\n* **[书籍](#kitaplar)**\n\n* **[竞赛（Kaggle 等）](#yarışmalar)**\n\n* **[移动应用](#mobil-uygulamalar)**\n\n## 基础主题\n* [基础：揭开黑箱——人工神经网络](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002F%C5%9Fu-kara-kutuyu-a%C3%A7alim-yapay-sinir-a%C4%9Flar%C4%B1-7b65c6a5264a)（Merve Ayyüce Kızrak）\n* [动机：人工智能与深度学习的故事](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fmotivasyon-yapay-zeka-ve-derin-%C3%B6%C4%9Frenme-48d09355388d)（Merve Ayyüce Kızrak）\n* [深度学习入门套装——硬件与软件](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F10\u002Fderin-ogrenme-baslangic-seti.html)（Arda Mavi）\n* [人工智能——思考与创造机器的诞生](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F09\u002Fyapay-zekanin-gelecegi.html)（Arda Mavi）\n* [人类与机器的学习](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Finsanda-ve-makinede-ogrenme.html)（Arda Mavi）\n* [计算机中的图像与数字序列](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fbilgisyarda-goruntu-ve-sayi-dizileri.html)（Arda Mavi）\n* [深度学习 1](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F10\u002Fderin-ogrenme-1.html)（Birol Kuyumcu）\n* [深度学习 2](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F11\u002Fderin-ogrenme-2.html)（Birol Kuyumcu）\n* [深度学习 3](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2015\u002F11\u002Fderin-ogrenme-3.html)（Birol Kuyumcu）\n* [深度学习、人工智能与计算机科学](http:\u002F\u002Fsayilarvekuramlar.blogspot.com\u002F2015\u002F12\u002Fbilgisayar-bilim-yapay-zeka.html)（Burak Bayramlı）\n* [机器学习很有趣](https:\u002F\u002Fmedium.com\u002Ft%C3%BCrkiye\u002Fmakine-%C3%B6%C4%9Frenimi-e%C4%9Flencelidir-2ad33ae37bea)（Özgür Şahin）\n* [机器学习很有趣 2](https:\u002F\u002Fmedium.com\u002Fbili%C5%9Fim-hareketi\u002Fmakine-%C3%B6%C4%9Frenimi-e%C4%9Flencelidir-2-k%C4%B1s%C4%B1m-6b464cbdf40c)（Atakan Yenel）\n* [什么是机器学习？](https:\u002F\u002Fmedium.com\u002Ftürkiye\u002Fmakine-öğrenmesi-nedir-20dee450b56e)（Halil İbrahim Şafak）\n* [机器学习 101](https:\u002F\u002Fveribilimcisi.com\u002Fmakine-ogrenmesi\u002F)（Seray Beşer）\n* [深度学习 101](https:\u002F\u002Fveribilimcisi.com\u002Fderin-ogrenme-101\u002F)（Seray Beşer）\n* [机器学习的数学基础](https:\u002F\u002Fveribilimcisi.com\u002Fmakine-ogrenmesi-matematigi\u002F)（Seray Beşer）\n* [成为数据科学家指南](http:\u002F\u002Fbilisim.io\u002F2017\u002F09\u002F28\u002Fveri-bilimcisi-olma-rehberi\u002F)（Şefik İlkin Serengil）\n* [Python：从零到精通编程](https:\u002F\u002Fwww.udemy.com\u002Fpython-sfrdan-uzmanlga-programlama-1\u002F)（Kaan Can Yılmaz）\n* [数据科学与 Python](https:\u002F\u002Fwww.udemy.com\u002Fdata-science-sfrdan-uzmanlga-veri-bilimi-2\u002F)（Kaan Can Yılmaz）\n* [数据可视化](https:\u002F\u002Fwww.udemy.com\u002Fdata-visualization-adan-zye-veri-gorsellestirme-3\u002F)（Kaan Can Yılmaz）\n* [机器学习](https:\u002F\u002Fwww.udemy.com\u002Fmachine-learning-ve-python-adan-zye-makine-ogrenmesi-4\u002F)（Kaan Can Yılmaz）\n\n## 算法\n\n### 算法实用技巧\n* [深度学习应用中最常用的超参数](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fderin-ogrenme-uygulamalarinda-en-sik-kullanilan-hiper-parametreler-ece8e9125c4)（Necmettin Çarkacı）\n* [深度学习应用中的性能优化方法（正则化）](https:\u002F\u002Fmedium.com\u002F@necmettin.carkaci\u002Fderin-öğrenme-uygulamalarında-başarım-iyileştirme-yöntemleri-regularization-fb521e64c30f)（Necmettin Çarkacı）\n\n### 人工神经网络\n* [人工神经网络入门](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fsinir-aglari.html)（Arda Mavi）\n* [人工神经网络](http:\u002F\u002Fwww.akanesen.com\u002F2017\u002F09\u002Fyapay-sinir-aglar.html)（Birol Akan Esen）\n* [人工神经网络基本概念：感知器、得分函数与损失函数](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fderin-öğrenme-uygulamalarında-temel-kavramlar-skor-ve-çarkacı\u002F)（Necmettin Çarkacı）\n* [神经网络：从历史错误中吸取教训](http:\u002F\u002Fbilisim.io\u002F2017\u002F07\u002F08\u002Fnoral-aglar-gecmis-hatalardan-dersler-cikarmak\u002F)（Şefik İlkin Serengil）\n* [神经网络学习算法详解：反向传播算法](http:\u002F\u002Fbilisim.io\u002F2017\u002F07\u002F11\u002Fnoral-aglar-ogrenme-algoritmasi-anlama-kilavuzu-geri-yayilim-algoritmasi\u002F)（Şefik İlkin Serengil）\n* [人工神经网络（Neural Network）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F08\u002F13\u002Fyapay-sinir-aglari\u002F)（Seray Beşer）\n* [感知器（Perceptron (P)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F08\u002F13\u002Fyapay-sinir-aglari\u002F#PERCEPTRON%20-%20ALGILAYICI)（Seray Beşer）\n* [前馈神经网络（Feed Forward (FF)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fileri-beslemeli-sinir-aglari-feedforward-neural-network\u002F)（Seray Beşer）\n* [循环神经网络（Recurrent Neural Network (RNN)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Ftekrarlayan-sinir-aglari-recurrent-neural-network\u002F)（Seray Beşer）\n* [深度前馈神经网络（Deep Feed Forward (DFF)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fderin-ileri-beslemeli-sinir-aglari-deep-feedforward-network\u002F)（Seray Beşer）\n* [长短期记忆网络（Long \u002F Short Term Memory (LSTM)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fuzun-kisa-sureli-bellek-long-short-term-memory\u002F)（Seray Beşer）\n* [径向基函数网络（Radial Basis Network (RBF)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fyaricapsal-temelli-ag-radial-basis-network\u002F)（Seray Beşer）\n* [门控循环单元（Gated Recurrent Unit (GRU)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkapili-tekrarlayan-hucre-gated-recurrent-unit\u002F)（Seray Beşer）\n* [自动编码器（Auto Encoder (AE)）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fotomatik-kodlayici-auto-encoder\u002F)（Seray Beşer）\n* [变分自动编码器（Variational AE (VAE)）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fvaryasyonel-otomatik-kodlayici-variational-autoencoder\u002F)（Seray Beşer）\n* [去噪自动编码器（Denoising AE (DAE)）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fgurultu-giderici-otomatik-kodlayici-denoising-autoencoder\u002F)（Seray Beşer）\n* [稀疏自动编码器（Sparse AE (SAE)）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fseyrek-otomatik-kodlayici-sparse-autoencoder\u002F)（Seray Beşer）\n* [马尔可夫链（Markov Chain (MC)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fmarkov-zinciri-markov-chain\u002F)（Seray Beşer）\n* [霍普菲尔德网络（Hopfield Network (HN)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fhopfield-agi-hopfield-network\u002F)（Seray Beşer）\n* [玻尔兹曼机（Boltzmann Machine (BM)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fboltzmann-makinesi-boltzmann-machine\u002F)（Seray Beşer）\n* [受限玻尔兹曼机（Restricted BM (RBM)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkisitli-boltzmann-makinesi-restricted-boltzmann-machine-rbm\u002F)（Seray Beşer）\n* [深度信念网络（Deep Belief Network (DBN)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fderin-inanc-agi-deep-belief-network\u002F)（Seray Beşer）\n* [卷积神经网络（Convolutional Neural Network (CNN)）](https:\u002F\u002Fveribilimcisi.com\u002F2017\u002F09\u002F26\u002Fkonvolusyonel-sinir-agi-convolutional-neural-network\u002F)（Seray Beşer）\n\n### 卷积神经网络\n* [深度对比：Inception与ResNet版本](http:\u002F\u002Fwww.ayyucekizrak.com\u002Fblogdetay\u002Fyapay-zeka-ve-derin-ogrenme-yazi-dizisi\u002Fderin-bir-karsilastirma-inception-ve-res-net-versiyonlari)（链接待更新！）（Merve Ayyüce Kızrak）\n* [深入更深处：卷积神经网络](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fderi%CC%87ne-daha-deri%CC%87ne-evri%C5%9Fimli-sinir-a%C4%9Flar%C4%B1-2813a2c8b2a9)（Merve Ayyüce Kızrak）\n* [卷积神经网络入门](http:\u002F\u002Fwww.ardamavi.com\u002F2017\u002F07\u002Fconvolutional-networks.html)（Arda Mavi）\n* [基于TensorFlow的Keras在MNIST数据集上的应用](http:\u002F\u002Ferdoganb.com\u002F2017\u002F04\u002Fkerastensorflow-ile-rakamlari-tanima-mnist-dataset\u002F)（Erdoğan Bavaş）\n* [卷积神经网络简要介绍](http:\u002F\u002Fbilisim.io\u002F2018\u002F01\u002F07\u002Fkonvolusyonel-noral-aglara-kisa-bir-giris\u002F)（Şefik İlkin Serengil）\n* [迁移学习：使用Keras实现Inception V3](http:\u002F\u002Fbilisim.io\u002F2018\u002F01\u002F22\u002Fogrenim-transferi-keras-ile-inception-v3-kullanimi\u002F)（Şefik İlkin Serengil）\n\n### 胶囊网络\n* [人工智能领域重大创新：胶囊网络（Capsule Networks）](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fyapay-zekan%C4%B1n-yeni-ve-%C3%A7ekici-mimarisi-kaps%C3%BCl-a%C4%9F%C4%B1na-uygulamal%C4%B1-bir-bak%C4%B1%C5%9F-ef7310e3d847)（Merve Ayyüce Kızrak）\n\n### 对抗生成网络\n* [对抗生成网络——GAN是什么？（土耳其语）](https:\u002F\u002Fmedium.com\u002F@mubuyuk51\u002Fgenerative-adversarial-networks-gan-nedir-t%C3%BCrk%C3%A7e-5819fe9c1fa7)（Muhammed Buyukkınacı）\n\n### 自动编码器\n* [人工神经网络：自动编码器](https:\u002F\u002Fwww.farukeroglu.org\u002F2018\u002F06\u002Fyapay-noral-aglar-autoencoder.html)（Faruk Eroğlu）\n* [自动编码器（Autoencoder）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fotomatik-kodlayici-auto-encoder\u002F)（Seray Beşer）\n* [去噪自动编码器（Denoising Autoencoder）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fgurultu-giderici-otomatik-kodlayici-denoising-autoencoder\u002F)（Seray Beşer）\n* [稀疏自动编码器（Sparse Autoencoder）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fseyrek-otomatik-kodlayici-sparse-autoencoder\u002F)（Seray Beşer）\n* [变分自动编码器（Variational Autoencoder）](https:\u002F\u002Fveribilimcisi.com\u002F2018\u002F06\u002F04\u002Fvaryasyonel-otomatik-kodlayici-variational-autoencoder\u002F)（Seray Beşer）\n\n\n\n## 应用领域\n### 自然语言处理\n* [使用Keras进行情感分析](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F10\u002Fkeras-ile-duygu-analizi.html)（Birol Kuyumcu）\n* [土耳其语文本处理初探](http:\u002F\u002Fwww.veridefteri.com\u002F2017\u002F11\u002F20\u002Fturkce-metin-islemede-ilk-adimlar\u002F)（İlker Birbil）\n\n### 网络安全\n* [利用深度学习技术检测分布式拒绝服务攻击](https:\u002F\u002Focatak.github.io\u002Fpapers\u002Fposter_foc.pdf)（Ferhat Özgür Çatak, Ahmet Fatih Mustaçoglu）\n\n### 计算机视觉\n* [光学字符识别、文字识别 (OCR)](https:\u002F\u002Fburakbayramli.github.io\u002Fdersblog\u002Falgs\u002Focr\u002Foptik_karakter_tanima_yazi_tanima__optical_character_recognition_ocr_.html)（Burak Bayramlı）\n* [YOLO：实时目标检测库（Darknet）安装](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fgercek-zamanli-nesne-tespiti-kutuphanesi-darknet-kurulumu)（Yavuz Kömeçoğlu）\n* [如何在 YOLO 中实现对我们自定义人物或物体的检测？](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fyolo-da-kendi-ozel-nesnemizin-algilanmasini-nasil-saglariz)（Yavuz Kömeçoğlu）\n* [如何开发图像识别移动应用？](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fg%C3%B6r%C3%BCnt%C3%BC-tan%C4%B1yan-mobil-uygulama-nas%C4%B1l-geli%C5%9Ftirilir-33760f7d827)（Özgür Şahin）\n* [10 分钟内开发图像分类移动应用](https:\u002F\u002Fmedium.com\u002Fnsistanbul\u002F10-dakikada-g%C3%B6r%C3%BCnt%C3%BC-s%C4%B1n%C4%B1fland%C4%B1ran-mobil-uygulama-geli%C5%9Ftirin-7567371839b0)（Özgür Şahin）\n\n## 框架\n### Caffe\n* [Caffe 使用指南——全面介绍 Caffe 的使用手册](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Fcaffe-klavuzu)（Birol Kuyumcu）\n* [Caffe 实用教程](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Fpratik-caffe)（Birol Kuyumcu）\n* [Caffe 微调：使用自己的数据集训练 Caffe 模型](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fcaffe-fine-tuning)（Yavuz Kömeçoğlu）\n* [Windows 操作系统下 Caffe 的安装](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fwindows-icin-caffe-kurulumu.html)（Mesut Pişkin）\n\n### Keras\n* [Keras 入门-1](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F01\u002Fkeras-giris-1.html)（Birol Kuyumcu）\n* [Keras 入门-2（LSTM）](http:\u002F\u002Fderindelimavi.blogspot.com.tr\u002F2017\u002F03\u002Fkerasa-giris-2-lstm.html)（Birol Kuyumcu）\n* [Keras 土耳其语文档](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fkeras_turkish_doc)（Kemalcan Bora）\n* [Keras 安装](http:\u002F\u002Fibrahimdelibasoglu.blogspot.com.tr\u002F2017\u002F08\u002Fpython-tensorflow-ile-keras-derin.html)（İbrahim Delibaşoğlu）\n* [使用 Keras 对声呐数据进行分类](http:\u002F\u002Fibrahimdelibasoglu.blogspot.com.tr\u002F2017\u002F09\u002Fkeras-ile-derin-ogrenmeye-giris-snflama.html)（İbrahim Delibaşoğlu）\n\n\n### TensorFlow\n* [TensorFlow 与深度学习入门](https:\u002F\u002Femredurukn.github.io\u002F2016\u002F11\u002F02\u002Ftensorflow-ile-derin-ogrenmeye-giris.html)（Emre Durukan）\n* [理解 TensorFlow](https:\u002F\u002Fmcemilg.github.io\u002Fgeneral\u002F2017\u002F11\u002F23\u002Ftensorflow\u002F)（M.Cemil Güney）\n* [TensorFlow 土耳其语教程文档](https:\u002F\u002Fgithub.com\u002FAelvangunduz\u002Ftensorflow_tutorials)（Ayse Elvan Aydemir）\n* [TensorFlow 101](https:\u002F\u002Fveribilimcisi.com\u002Ftensorflow-101\u002F)（Seray Beşer）\n\n\n### PyTorch\n* [PyTorch 与深度学习入门：安装](https:\u002F\u002Fmedium.com\u002F@ozgungenc\u002Fpytorch-ile-derin-%C3%B6%C4%9Frenmeye-giri%C5%9F-kurulum-2194a06ce0c)（Özgün Genç）\n\n### Deeplearning4j\n* [Deeplearning4j 与深度学习入门](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fdeeplearning4j-ile-derin-ogrenmeye-giris.html)（Mesut Pişkin）\n* [Deeplearning4j 架构](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fdeeplearning4j-mimarisi-ve-kurulum.html)（Mesut Pişkin）\n* [Deeplearning4j 与人工神经网络](http:\u002F\u002Fmesutpiskin.com\u002Fblog\u002Fyapay-sinir-agi-derin-ogrenme.html)（Mesut Pişkin）\n\n### FANN\n* [FANN 工具使用指南](https:\u002F\u002Fwww.slideshare.net\u002Fbluekid\u002Ffann-tool-klavuzu)（Birol Kuyumcu）\n\n## 硬件与云支持\n\n### 硬件\n\n#### NVIDIA Titan 系列\n\n#### NVIDIA Jetson TX 系列\n\n#### Intel-Movidius Neural Compute Stick\n* [Intel-Movidius Neural Compute Stick 是什么？如何使用？](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fintel-movidius-neural-compute-stick-nedir-ve-nas%C4%B1l-kullan%C4%B1l%C4%B1r-85fc9af6dc26)（Merve Ayyüce Kızrak）\n* [在 Raspberry Pi 3 上使用 Intel Movidius Neural Compute Stick 运行深度学习应用](http:\u002F\u002Fblog.yavuzz.com\u002Fpost\u002Fraspberry-pi-3-uzerinde-intel-movidius-neural-compute-stick-ile-derin-ogrenme-uygulamalari-calistirma)（Yavuz Kömeçoğlu）\n\n### 云\n\n#### Google Colaboratory\n* [使用 Google Colab 免费获得 GPU 资源](https:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye\u002Fgoogle-colab-ile-%C3%BCcretsiz-gpu-kullan%C4%B1m%C4%B1-30fdb7dd822e)（Fuat）\n### 深度学习系统准备与安装指南\n#### 显卡驱动、CUDA 和 cuDNN 的安装\n* [NVIDIA GPU 驱动、CUDA 和 cuDNN 安装指南](https:\u002F\u002Fgithub.com\u002Fearcz\u002FNVIDIA-GPU-Surucusu-ve-CUDA-Yukleme)（Ender Ayhan Rencüzoğulları）\n\n#### Microsoft Azure Notebook\n\n## 科学论文\n### 综述类\n* [关于深度学习方法及其应用的综述](http:\u002F\u002Fdergipark.gov.tr\u002Fdownload\u002Farticle-file\u002F394923)（Abdulkadir Şeker、Banu Diri、Hasan Hüseyin Balık）\n\n### 计算机视觉\n* [MARVEL：用于海上船舶的大规模图像数据集](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-54193-8_11)（Erhan Gündoğdu、Berkan Solmaz、Veysel Yücesoy、Aykut Koç）\n* [基于深度学习特征降维的人脸识别分类器](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7960368\u002F)（Ahmet Bilgiç、Onur Can Kurban、Tülay Yıldırım）\n* [基于深度学习的签名识别应用](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960454\u002F)（Nurullah Çalık、\nOnur Can Kurban、Ali Rıza Yılmaz、Lütfiye Durak Ata、Tülay Yıldırım）\n* [关于叶片识别：CNN 与传统机器学习方法的比较](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960257\u002F)（Mohamed Abbas Hedjazi、Ikram Kourbane、Yakup Genç）\n* [关于叶片识别：CNN 与传统机器学习方法的比较](https:\u002F\u002Fweb.cs.hacettepe.edu.tr\u002F~aykut\u002Fpapers\u002Fieee-tmm17.pdf)（Çağdaş Bak、Aysun Koçak、Erkut Erdem、Aykut Erdem）\n* [利用卷积滤波器模式进行迁移学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06973)（Mehmet Aygün、Yusuf Aytar、Hazım Kemal Ekenel）\n* [无约束耳部识别挑战赛](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06997)（Žiga Emeršič、Dejan Štepec、Vitomir Štruc、Peter Peer、Anjith George、Adil Ahmad、Elshibani Omar、Terrance E. Boult、Reza Safdari、Yuxiang Zhou、Stefanos Zafeiriou、Dogucan Yaman、Fevziye I. Eyiokur、Hazim K. Ekenel）\n* [结合 LiDAR 空间聚类和卷积神经网络进行行人检测](https:\u002F\u002Farxiv.org\u002Fabs\u002F1710.06160)（Damien Matti、Hazım Kemal Ekenel、Jean-Philippe Thiran）\n* [结合多视角进行视觉语音识别](http:\u002F\u002Favsp2017.loria.fr\u002Fwp-content\u002Fuploads\u002F2017\u002F07\u002FAVSP2017_paper_25.pdf)（Marina Zimmermann、Mostafa Mehdipour Ghazi、Hazım Kemal Ekenel、Jean-Philippe Thiran）\n* [用于定位和分类街道垃圾的计算机视觉系统](https:\u002F\u002Finfoscience.epfl.ch\u002Frecord\u002F231365\u002Ffiles\u002FA-Computer-Vision-System%20to-Localize-and-Classify-Wastes-on-the-Streets.pdf)（Mohammad Saeed Rad、Andreas von Kaenel、Andre Droux、Francois\nTieche、Nabil Ouerhani、Hazım Kemal Ekenel、Jean-Philippe Thiran）\n\n### 土耳其语自然语言处理\n* [土耳其语词汇表示中的语言学特征](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7960223\u002F)（奥努尔·京格尔、埃雷伊·耶尔德兹）\n* [面向形态丰富语言的命名实体识别的形态嵌入](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.00506)（奥努尔·京格尔、埃雷伊·耶尔德兹、苏赞·于斯屈达尔勒、通加·京格尔）\n* [适用于python3.x的Zemberek语法分析器](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fzemberek_parser)（凯马尔詹·博拉）\n* [一种考虑形态信息的网络用于形态消歧](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.03654.pdf)（埃雷伊·耶尔德兹、恰格拉尔·特尔卡兹、H·巴哈迪尔·沙欣、穆斯塔法·托尔加·埃伦、奥赞·松梅兹）\n* [利用大规模地名词典自动标注的土耳其语命名实体识别与文本分类语料库](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.02363.pdf)（H·巴哈迪尔·沙欣、恰格拉尔·特尔卡兹、埃雷伊·耶尔德兹、穆斯塔法·托尔加·埃伦、奥赞·松梅兹）\n* [土耳其语与自然语言处理](http:\u002F\u002Fdergipark.gov.tr\u002Fdownload\u002Farticle-file\u002F207207)（凯马尔·奥夫拉泽尔）\n* [土耳其语及其在语言处理中的挑战](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10579-014-9267-2)（凯马尔·奥夫拉泽尔）\n* [Zemberek Docker REST服务端](https:\u002F\u002Fgithub.com\u002Fcbilgili\u002Fzemberek-nlp-server)（詹贝·比尔吉利）\n\n### 语音处理\n* [针对古典土耳其音乐调式的音乐信息检索系统](http:\u002F\u002Fjournals.sagepub.com\u002Fdoi\u002Fabs\u002F10.1177\u002F0037549717708615?journalCode=simb)（梅尔韦·艾于杰·克兹拉克、布伦特·博拉）\n\n### 预测\n* [利用卷积神经网络和特征相关性对伊斯坦布尔证券交易所日内价格的预测](http:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0950705117304252)（哈坎·金杜兹、尤瑟夫·亚斯兰、泽赫拉·恰塔尔泰佩）\n\n### 网络安全\n* [使用深度学习技术检测分布式拒绝服务攻击](https:\u002F\u002Focatak.github.io\u002Fpapers\u002Fposter_foc.pdf)（费尔哈特·厄兹居尔·恰塔克、艾哈迈德·法提赫·穆斯塔乔卢）\n* [CPP-ELM：面向云系统的加密隐私保护极限学习机](http:\u002F\u002Fwww.atlantis-press.com\u002Fjournals\u002Fijcis\u002F25885040)（费尔哈特·厄兹居尔·恰塔克、艾哈迈德·法提赫·穆斯塔乔卢）\n\n## 数据集\n* [手语数字数据集](https:\u002F\u002Fgithub.com\u002Fardamavi\u002FSign-Language-Digits-Dataset)（土耳其安卡拉阿扬吉安纳多卢高中——泽内普·迪克莱与阿尔达·马维）\n* [MARVEL：大型海事船舶图像数据集](https:\u002F\u002Fgithub.com\u002Favaapm\u002Fmarveldataset2016)（埃尔汗·金多乌杜、贝尔坎·索尔马兹、韦塞尔·于杰索伊、艾库特·科奇）\n* [伊斯坦布尔技术大学KEMİK自然语言处理小组数据集](http:\u002F\u002Fwww.kemik.yildiz.edu.tr\u002F?id=28)（YTÜ KEMİK自然语言处理小组）\n* [TTC-3600：一个新的土耳其语文本分类基准数据集]（https:\u002F\u002Fgithub.com\u002Fdenopas\u002FTTC-3600）（代尼兹·克勒恩奇、阿肯·厄兹奇夫特、法特玛·博兹伊吉特、佩林·耶尔德勒姆、法提赫·于查拉尔、埃明·博兰达格）\n* [土耳其语情感数据集](http:\u002F\u002Fwww.baskent.edu.tr\u002F~msert\u002Fresearch\u002Fdatasets\u002FSentimentDatasetTR.html)（艾哈迈德·海兰、穆斯塔法·塞特）\n* [英语\u002F土耳其语维基百科命名实体识别与文本分类数据集](https:\u002F\u002Fdata.mendeley.com\u002Fdatasets\u002Fcdcztymf4k\u002F1)（H·巴哈迪尔·沙欣、恰格拉尔·特尔卡兹、埃雷伊·耶尔德兹、穆斯塔法·托尔加·埃伦、奥赞·松梅兹）\n* [土耳其语NLP数据集](https:\u002F\u002Ftscorpus.com)（塞泽尔，B.，塞泽尔，T. 2013. TS语料库：人人可用的土耳其语汇编。第27届全国语言学会议论文集。2013年5月3日至4日，安塔利亚，凯梅尔：哈切特佩大学英语语言学系。页码：217–225）\n* [包含10亿个词元的土耳其语语料库及土耳其语词向量和类比推理任务对](https:\u002F\u002Fgithub.com\u002Fonurgu\u002Flinguistic-features-in-turkish-word-representations\u002Freleases)（奥努尔·京格尔、埃雷伊·耶尔德兹，《土耳其语词汇表示中的语言学特征》，SIU，安塔利亚，2017年）\n* [代尼兹·于雷特整理的土耳其语语言资源](http:\u002F\u002Fwww.denizyuret.com\u002F2006\u002F11\u002Fturkish-resources.html)\n* [中东技术大学-萨班哲土耳其树库](https:\u002F\u002Fweb.itu.edu.tr\u002Fgulsenc\u002Ftreebanks.html)\n* [SemEval-2016 ABSA电信推文-土耳其语：测试数据-第一阶段（子任务1）](http:\u002F\u002Fmetashare.ilsp.gr:8080\u002Frepository\u002Fbrowse\u002Fsemeval-2016-absa-telecom-tweets-turkish-test-data-phase-a-subtask-1\u002F5343e408ba0811e5ab4f842b2b6a04d71f53ece5fa7a4dd286e99e539ac3e27f\u002F)\n* [SemEval-2016 ABSA餐厅评论-土耳其语：训练数据（子任务1）](http:\u002F\u002Fmetashare.ilsp.gr:8080\u002Frepository\u002Fbrowse\u002Fsemeval-2016-absa-restaurant-reviews-turkish-train-data-subtask-1\u002Fff5dad70676311e5bf9c842b2b6a04d71fa7fa3ba4504a228dafe0c24560585b\u002F)\n* [土耳其语释义语料库（TuPC）](https:\u002F\u002Fosf.io\u002Fwp83a\u002F)（埃耶焦卢，阿斯莉，以及比尔·凯勒。“ASOBEK在SemEval-2016任务1中的应用：基于字符N-gram嵌入的句子表示用于语义文本相似度。”SemEval@ NAACL-HLT。2016年）\n* [土耳其语WordNet（KeNet）](http:\u002F\u002Fhaydut.isikun.edu.tr\u002Fkenet.html)（萨斯马兹，E.，R. 埃赫萨尼，O. T. 耶尔德兹，“从维基百科和维基词典中提取上位词”，SIU，安塔利亚，土耳其，2017年）\n* [帕金森病语音数据集，包含多种录音类型](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002FParkinson%2BSpeech%2BDataset%2Bwith%2B%2BMultiple%2BTypes%2Bof%2BSound%2BRecordings#)（埃尔多古·萨卡尔，B.，伊森库尔，M.，萨卡尔，C.O.，塞尔特巴斯，A.，古尔根，F.，德利尔，S.，阿帕伊丁，H.，库尔孙，O.，“收集并分析包含多种录音类型的帕金森病语音数据集”，IEEE生物医学与健康信息学期刊，第17卷第4期，页码828–834，2013年）\n* [土耳其学生评估数据集](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fturkiye+student+evaluation#)（金杜兹，G. & 福库埃，E.（2013年））\n* [联合循环发电厂数据集](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fcombined+cycle+power+plant)（皮纳尔·图费克奇，利用机器学习方法预测基础负荷运行的联合循环发电厂满载时的电功率输出，国际电力与能源系统期刊，第60卷，2014年9月，页码126–140，ISSN 0142-06）\n* [皮肤病学数据集](http:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Fdermatology)（G. 德米罗兹、H. A. 戈韦尼尔和N. 伊尔特，“利用投票特征区间学习红斑鳞状疾病的鉴别诊断”，1998年至2004年间发表于《医学人工智能》杂志）\n* [心律失常数据集](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002Farrhythmia)（H. 阿尔泰·古韦尼尔、布拉克·阿贾尔、古尔森·德米罗兹、艾汉·切金“一种用于心律失常分析的监督式机器学习算法”。1997年瑞典隆德心脏计算机会议论文集）\n* [人造角色数据集](https:\u002F\u002Farchive.ics.uci.edu\u002Fml\u002Fdatasets\u002FArtificial+Characters)（H. 阿尔泰·古韦尼尔等人，1992年）\n* [土耳其自然语言处理工具包——内置于Zemberek中](http:\u002F\u002Fwww.aliok.com.tr\u002Fprojects\u002F2014-10-02-trnltk.html)\n* [235,000条土耳其产品评论](https:\u002F\u002Fgithub.com\u002Ffthbrmnby\u002Fturkish-text-data)\n* [ODP TR-30土耳其搜索结果聚类数据集](https:\u002F\u002Fgithub.com\u002Ffaraday\u002Fodp-tr30)（Ç. 恰勒，2010年）\n* [Modacruz和Zara服装数据集](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fflora_fashion_scraping)（凯马尔詹·博拉）\n## 视频课程\n\n### 综合\n* [安卡拉深度学习 - 深度学习活动1](https:\u002F\u002Fyoutu.be\u002FK74rzKSsGs8)（费哈特·库尔特）{96分钟}\n* [中东技术大学图像分析应用与研究中心（OGAM）2016年暑期学校](http:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fvideolar)（中东技术大学）\n\n### 人工神经网络\n* [神经网络1：训练与概念入门](https:\u002F\u002Fyoutu.be\u002FB5MmXmMMuvI)（萨迪·埃夫伦·塞克尔博士 @BilgisayarKavramlari）{23分钟}\n* [神经网络2：感知器概念与学习](https:\u002F\u002Fyoutu.be\u002F5Lo_HUDtxtw)（萨迪·埃夫伦·塞克尔博士 @BilgisayarKavramlari）{13分钟}\n* [神经网络3：多层人工神经网络](https:\u002F\u002Fyoutu.be\u002FqrmaixHBrzU)（萨迪·埃夫伦·塞克尔博士 @BilgisayarKavramlari）{13分钟}\n* [人工神经网络的数学原理及18行代码实现](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=icrcbqPNrNE\u002F)（梅赫梅特·布拉克·萨伊杰）\n\n### 人工智能\n* [人工智能（Artificial Intelligence）- 播放列表](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLh9ECzBB8tJOtaD6DFxqRdP7QHIaBFcbW)（萨迪·埃夫伦·塞克尔博士 @BilgisayarKavramlari）{48个视频}\n* [人工智能与深度学习](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qk1RjRLIAq4)（梅尔韦·艾于哲·克兹拉克）{68分钟}\n* [人工智能时代 | TEDxMETUAnkara](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=d4kQVyAEsqA)（谢达·埃尔特金博士）{18分钟}\n\n### 计算机视觉\n* [遥感影像像素级分类 第1\u002F2部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Y087JVjzw-Y)（埃尔汗·阿卜杜拉（Erchan Aptoula）@Data İstanbul）{60分钟}\n* [遥感影像像素级分类 第2\u002F2部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EAYNMnMBqnA)（埃尔汗·阿卜杜拉（Erchan Aptoula）@Data İstanbul）{30分钟}\n* [深入探讨深度学习](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zJPW6Lyf_Xs)（谢菲克·伊尔金·塞伦吉尔 @Softtech Sahnesi）{52分钟}\n* [机器学习时代的生存指南](https:\u002F\u002Fyoutu.be\u002FP2MwuGpRgSQ)（谢菲克·伊尔金·塞伦吉尔 @İstanbul Coding Talks）{84分钟}\n* [深度学习：过去、现在、未来](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ITCD2Z4jT8w)（谢菲克·伊尔金·塞伦吉尔 @计算机工程师协会）{100分钟}\n* [使用Keras构建卷积神经网络](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e\u002F)（梅赫梅特·布拉克·萨伊杰）\n* [使用Keras构建卷积神经网络](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e\u002F)（梅赫梅特·布拉克·萨伊杰）\n\n### 物联网\n* [物联网与深度学习活动](https:\u002F\u002Fyoutu.be\u002Ffqf6m3R4psQ)（费哈特·库尔特）{82分钟}\n\n## 框架\n### Keras\n* [Keras视频教程系列](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RNWjwdEQHOQ&list=PLRRY18KNZTgUyaxSRvExF7zNsIpaehl5e)（梅赫梅特·布拉克·萨伊杰）{21个视频，持续更新}\n\n### Julia\n* [Julia与Knet入门深度学习](https:\u002F\u002Fyoutu.be\u002F3TR3Rx-Esis)（丹尼斯·尤雷特副教授）{104分钟}\n\n### MatConvNet\n* [MatConvNet与Matlab入门深度学习](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=nRVQQNw4Kh4&t=8s)（艾哈迈德·格坎·波伊拉兹）{5个视频，后续会继续添加}\n\n## 演示文稿\n* [2017年博兹基尔人工智能暑期学校 - 演示文稿](http:\u002F\u002Fgoo.gl\u002Fo2H9hA)（HUCVL）\n* [2016年中东技术大学图像分析应用与研究中心（OGAM）暑期学校 - 演示文稿](https:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fsunumlar)（中东技术大学）\n* [2016年中东技术大学图像分析应用与研究中心（OGAM）暑期学校 - 视频](http:\u002F\u002Fobayo.ogam.metu.edu.tr\u002Fvideolar)（中东技术大学）\n* [深度学习土耳其 - 统计语言处理 - 凯马尔·奥夫拉泽教授 - 演示文稿](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1w0L5r_C0BA1VLP8uA2iPNl90F8lXkMuc?usp=sharing)（DLTR）\n\n## Github\n### 自然语言处理\n* [Python3版Zemberek分词器](https:\u002F\u002Fgithub.com\u002Fkemalcanbora\u002Fzemberek_parser)（凯马尔詹·博拉）\n* [包含90万条数据的土耳其语词嵌入](https:\u002F\u002Fgithub.com\u002Fsavasy\u002FTurkishWordEmbeddings)（萨瓦斯·Y）\n* [用于土耳其语的有限状态形态分析器](https:\u002F\u002Fgithub.com\u002Fcoltekin\u002FTRmorph)（查格里·乔尔特金）\n* [使用Keras进行土耳其语情感分析（正面-负面）](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTurkce-Anlam-Analizi)（泽基·库什）\n\n### 搜索算法\n* [用C语言实现无信息\u002F盲目搜索算法](https:\u002F\u002Fgithub.com\u002FEnes1313\u002FUninformed-Search-Strategies)（埃内斯·艾丁）\n\n### 计算机视觉\n* [使用CNN进行图像分类](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FCaffeClassification)（梅苏特·皮什金）\n* [实时性别检测](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FGenderClassification)（梅苏特·皮什金）\n* [情感与性别识别](https:\u002F\u002Fgithub.com\u002Fayyucekizrak\u002FDuygu-Cinsiyet_Tanima-Emotion-Gender_Recognition)（梅尔韦·艾于哲·克兹拉克-亚武兹·科梅乔卢）\n* [使用TensorFlow-CNN对CIFAR10数据集进行分类及参数分析](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTensorflow-CNN-with-CIFAR10-Dataset)（泽基·库什）\n* [使用TensorFlow-CNN对FashionMNIST数据集进行分类](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FTensorflow-CNN-with-FashionMNIST-Dataset)（泽基·库什）\n* [使用Keras-CNN对CIFAR10数据集进行分类](https:\u002F\u002Fgithub.com\u002Fzekikus\u002FKeras-CNN-with-CIFAR10-Dataset)（泽基·库什）\n\n### 神经网络\n* [使用反馈式人工神经网络进行字符识别](https:\u002F\u002Fgithub.com\u002Fmesutpiskin\u002FANNCharacterRecognition)（梅苏特·皮什金）\n* [用C++实现人工神经网络](https:\u002F\u002Fgithub.com\u002FEnes1313\u002FCpp-ile-YSA)（埃内斯·艾丁）\n* [机器学习](https:\u002F\u002Fgithub.com\u002FSerayBeser\u002FMakine-Ogrenmesi)（塞莱·贝塞尔）\n\n## 博客\n* [深度学习土耳其博客](http:\u002F\u002Fmedium.com\u002Fdeep-learning-turkiye)\n* [veridefteri.com](http:\u002F\u002Fveridefteri.com\u002F)\n* [zekimakine.com](http:\u002F\u002Fzekimakine.com\u002F)\n* [veribilimcisi.com](https:\u002F\u002Fveribilimcisi.com\u002F)\n* [alpslabel.wordpress.com](https:\u002F\u002Falpslabel.wordpress.com\u002F\u002F)\n* [makineogrenimi.wordpress.com](https:\u002F\u002Fmakineogrenimi.wordpress.com)\n* [devhunteryz.wordpress.com](https:\u002F\u002Fdevhunteryz.wordpress.com)\n\n## 图书\n* [机器学习 - 埃森·阿尔帕伊丁](http:\u002F\u002Fwww.idefix.com\u002FKitap\u002FYapay-Ogrenme\u002FEthem-Alpaydin\u002FBilim\u002FPopuler-Bilim\u002Furunno=0000000362293)\n* [深度学习 - 伊恩·古德费洛、约书亚·本吉奥、亚伦·库维尔](https:\u002F\u002Fwww.kitapyurdu.com\u002Fkitap\u002Fderin-ogrenme-ciltli\u002F480279.html)\n* [OpenCV图像处理与机器学习 - 比罗尔·库尤姆久](http:\u002F\u002Fwww.kitapyurdu.com\u002Fkitap\u002Fopencv-goruntu-isleme-ve-yapay-ogrenme\u002F376463.html)\n* [人工智能 - 瓦西夫·瓦吉福格鲁·纳比耶夫](http:\u002F\u002Fwww.dr.com.tr\u002FKitap\u002FYapay-Zeka-Problemler-Yontemler-Algoritma-\u002FVasif-Vagifoglu-Nabiyev\u002FBilim\u002FPopuler-Bilim\u002Furunno=0000000435115)\n\n## 竞赛\n* [我在Kaggle竞赛中的经验与观察](https:\u002F\u002Fburakozdemir.co.uk\u002Farticle\u002Fkaggle-yarisma-deneyimim-ve-gozlemlerim)（布拉克·厄兹代米尔）\n* [Kaggle BNP Paribas第93名（前3%）方法与代码](https:\u002F\u002Fdatanoord.wordpress.com\u002F2016\u002F05\u002F05\u002Fkaggle-bnp-paribas-93-derece-top-3-yontem-ve-kod\u002F)（艾雪·埃尔万·阿尔德米尔）\n\n## 移动应用\n* [视障人士钞票识别器](https:\u002F\u002Fitunes.apple.com\u002Ftr\u002Fapp\u002Fpara-okuyucu\u002Fid1334298365?l=tr&mt=8)（厄兹居尔·沙欣）\n* [VisionDict](https:\u002F\u002Fitunes.apple.com\u002Ftr\u002Fapp\u002Fvisiondict\u002Fid1299943619?mt=8)（卡迪尔·梅尔特·巴鲁特丘奥卢）","# turkce-yapay-zeka-kaynaklari 快速上手指南\n\n**工具说明**：`turkce-yapay-zeka-kaynaklari` 并非一个可安装的软件库或框架，而是一个由 **Deep Learning Türkiye** 社区维护的**开源资源索引仓库**。它汇集了土耳其语的深度学习和机器学习教程、文章、数据集、代码示例及视频课程。\n\n本指南旨在帮助中国开发者高效利用该仓库中的学习资源，特别是其中包含的通用算法原理和代码实现部分。\n\n## 环境准备\n\n由于该仓库主要提供学习链接和参考代码（多基于 Python），您需要准备以下开发环境以运行仓库中引用的示例代码：\n\n*   **操作系统**：Windows, macOS 或 Linux\n*   **编程语言**：Python 3.6+\n*   **核心依赖**：\n    *   `TensorFlow` 或 `PyTorch` (根据具体教程要求)\n    *   `Keras`\n    *   `NumPy`, `Pandas`, `Matplotlib`\n*   **网络环境**：部分原始链接为土耳其语网站，建议使用浏览器翻译插件辅助阅读。代码部分通常通用，不受语言限制。\n\n> **国内加速建议**：\n> 在安装 Python 依赖时，推荐使用国内镜像源以提升下载速度：\n> ```bash\n> pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple tensorflow keras numpy pandas matplotlib\n> ```\n\n## 安装步骤\n\n您无需安装该“工具”本身，只需克隆仓库以获取资源列表和本地可能存在的代码示例。\n\n1.  **克隆仓库**\n    打开终端，执行以下命令：\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002Ffurkanakdemir\u002Fturkce-yapay-zeka-kaynaklari.git\n    ```\n\n2.  **进入目录**\n    ```bash\n    cd turkce-yapay-zeka-kaynaklari\n    ```\n\n3.  **浏览资源**\n    直接打开根目录下的 `README.md` 文件（或使用 Markdown 阅读器），查看分类清晰的资源列表。重点关注的章节包括：\n    *   `ALGORİTMALAR` (算法)：包含 ANN, CNN, RNN, GAN 等详细教程链接。\n    *   `KULLANIM ALANLARI` (应用领域)：涵盖 NLP、计算机视觉、网络安全等实战案例。\n    *   `Github`：指向具体的代码实现仓库。\n\n## 基本使用\n\n该项目的核心用法是**按图索骥**，根据您想学习的算法主题，找到对应的教程链接或代码仓库进行实践。\n\n### 示例：学习卷积神经网络 (CNN)\n\n假设您想学习 CNN 的原理并运行一个简单的图像识别示例：\n\n1.  **查找资源**：\n    在 `README.md` 的 `Evrişimli Sinir Ağları (Convolutional Neural Networks)` 章节下，找到如下资源（示例）：\n    *   教程：*Derine Daha Derine: Evrişimli Sinir Ağları* (深入卷积神经网络)\n    *   代码示例：*Tensorflow Tabanlı Keras ile MNIST Veriseti Üzerinde Çalışma* (基于 TensorFlow\u002FKeras 的 MNIST 数据集实战)\n\n2.  **获取代码**：\n    点击教程中提供的外部链接（通常是博客或子 GitHub 仓库）。如果链接指向具体的 GitHub 代码库，克隆该代码库：\n    ```bash\n    # 假设找到的具体代码仓库地址如下（仅为示例逻辑）\n    git clone \u003C具体教程对应的代码仓库 URL>\n    cd \u003C具体教程对应的代码仓库目录>\n    ```\n\n3.  **运行示例**：\n    安装该特定示例所需的依赖（通常项目内会有 `requirements.txt`）：\n    ```bash\n    pip install -r requirements.txt\n    ```\n    运行主程序（通常为 `.py` 文件或 Jupyter Notebook）：\n    ```bash\n    python main.py\n    # 或者\n    jupyter notebook tutorial.ipynb\n    ```\n\n### 示例：查阅算法理论\n\n如果您需要查阅 **LSTM (长短期记忆网络)** 的数学原理或结构图解：\n\n1.  在 `README.md` 的 `Yapay Sinir Ağları` (人工神经网络) 列表中定位到：\n    *   `[Uzun \u002F Kısa Süreli Bellek (Long \u002F Short Term Memory (LSTM))](https:\u002F\u002Fveribilimcisi.com\u002F...)`\n2.  直接在浏览器打开链接。\n3.  利用浏览器的**自动翻译功能**将土耳其语内容转换为中文或英文，即可阅读关于 LSTM 门控机制、公式推导及应用场景的详细讲解。\n\n---\n**提示**：虽然文档语言为土耳其语，但其中的**代码片段 (Code Snippets)**、**数学公式**以及**架构图**是全球通用的。对于中国开发者，建议重点关注代码实现部分，并结合通用的深度学习理论知识进行对照学习。","一位居住在土耳其的计算机系大学生，正试图从零开始学习深度学习以完成毕业设计，但他发现主流的英文技术文档门槛过高，而本地化的优质教程又极其分散。\n\n### 没有 turkce-yapay-zeka-kaynaklari 时\n- **语言障碍导致入门受阻**：面对全英文的学术论文和官方文档，因专业术语理解困难，花费大量时间查词典却仍难以构建完整的知识体系。\n- **资源检索效率极低**：需要在谷歌、YouTube 和各个独立博客间反复切换搜索，难以辨别哪些土耳其语教程是系统性的，哪些只是碎片化信息。\n- **缺乏本土化实践指引**：找不到针对土耳其本地硬件环境或云服务的配置指南，在搭建开发环境阶段就因兼容性问题屡屡受挫。\n- **社区支持缺失**：遇到算法实现 bug 时，无法找到用母语交流的技术社区或相关案例参考，陷入孤立无援的调试困境。\n\n### 使用 turkce-yapay-zeka-kaynaklari 后\n- **母语学习路径清晰**：直接利用平台整理的“基础主题”和\"101 系列”文章（如 Seray Beşer 的教程），用土耳其语快速掌握了神经网络数学原理和核心概念。\n- **一站式资源聚合**：通过分类清晰的目录，瞬间定位到高质量的本地视频课程、GitHub 代码库及数据集，将原本数周的资料搜集工作缩短至几小时。\n- **落地实操有章可循**：参考 Arda Mavi 等专家撰写的硬件与软件起步指南，顺利完成了本地开发环境的搭建，并获得了针对本地云服务的部署建议。\n- **融入活跃技术生态**：顺藤摸瓜加入了 Deep Learning Türkiye 社区，在 LinkedIn 和论坛上与本土开发者互动，迅速解决了模型训练中的具体报错问题。\n\nturkce-yapay-zeka-kaynaklari 通过聚合高质量的本土化内容，消除了语言与文化壁垒，让土耳其开发者能以母语高效跨越从理论到实践的鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdeeplearningturkiye_turkce-yapay-zeka-kaynaklari_b611b84c.png","deeplearningturkiye","Deep Learning Türkiye","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fdeeplearningturkiye_dcd91290.png","Türkiye'nin En Büyük Yapay Zeka Topluluğu \u002F Turkey's Leading Artificial Intelligence Community",null,"İstanbul","http:\u002F\u002Fdeeplearningturkiye.com\u002F","https:\u002F\u002Fgithub.com\u002Fdeeplearningturkiye",2417,447,"2026-04-14T16:26:41","MIT",1,"","未说明",{"notes":88,"python":86,"dependencies":89},"该项目并非一个可执行的软件工具或代码库，而是一个由 Deep Learning Türkiye 社区维护的土耳其语人工智能资源索引列表（包含博客文章、视频教程、科学论文、数据集等链接）。因此，它没有特定的操作系统、GPU、内存、Python 版本或依赖库要求。用户仅需通过浏览器访问提供的链接即可阅读相关学习资料。",[],[14,35],[92,93,94,95,96,97,98,99,100,101,102,103],"deep-learning","convolutional-neural-networks","tensorflow","pytorch","caffe","keras","machine-learning","derin-ogrenme","makine-ogrenmesi","yapay-zeka","dogal-dil-isleme","natural-language-processing","2026-03-27T02:49:30.150509","2026-04-19T06:06:47.278379",[],[]]