[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Swift-AI--Swift-AI":3,"tool-Swift-AI--Swift-AI":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":67,"owner_name":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":78,"owner_twitter":78,"owner_website":78,"owner_url":79,"languages":80,"stars":85,"forks":86,"last_commit_at":87,"license":88,"difficulty_score":23,"env_os":89,"env_gpu":90,"env_ram":90,"env_deps":91,"category_tags":95,"github_topics":96,"view_count":23,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":104,"updated_at":105,"faqs":106,"releases":137},1975,"Swift-AI\u002FSwift-AI","Swift-AI","The Swift machine learning library.","Swift-AI 是一个完全用 Swift 编写的深度学习库，专为 Apple 平台设计。它让 Swift 开发者无需切换语言，即可在 iOS、macOS 等设备上高效构建机器学习应用，当前支持所有 Apple 平台，Linux 支持即将推出。核心模块 NeuralNet 支持全连接神经网络，针对 Apple 硬件深度优化，利用 Accelerate 框架实现高速矩阵运算和并行处理。例如，提供 MNIST 手写识别和 iOS 手写识别的示例项目，直接运行即可体验。适合 iOS\u002FmacOS 开发者、Swift 工程师及需要快速验证 AI 想法的科研人员。未来将扩展卷积神经网络、循环神经网络等模块。","![Banner](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSwift-AI_Swift-AI_readme_872cb7ffa7db.png)\n\nSwift AI is a high-performance deep learning library written entirely in Swift. We currently offer support for all Apple platforms, with Linux support coming soon.\n\n## Tools\nSwift AI includes a collection of common tools used for artificial intelligence and scientific applications:\n\n - [x] [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet)\n    * A flexible, fully-connected neural network with support for deep learning\n    * Optimized specifically for Apple hardware, using advanced parallel processing techniques\n - [ ] Convolutional Neural Network\n - [ ] Recurrent Neural Network\n - [ ] Genetic Algorithm Library\n - [ ] Fast Linear Algebra Library\n - [ ] Signal Processing Library\n\n## Example Projects\nWe've created some example projects to demonstrate the usage of Swift AI. Each resides in their own repository and can be built with little or no configuration:\n\n - [NeuralNet-MNIST](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet-MNIST)\n    * A [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet) training example for the [MNIST](http:\u002F\u002Fyann.lecun.com\u002Fexdb\u002Fmnist\u002F) handwriting database\n    * Trains a neural network to recognize handwritten digits\n    * Built for macOS\n - [NeuralNet-Handwriting-iOS](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet-Handwriting-iOS)\n    * A demo for handwriting recognition using [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet)\n    * Pre-trained; just download and run\n    * Built for iOS\n\n## Usage\nEach module now contains its own documentation. We recommend that you read the docs carefully for detailed instructions on using the various components of Swift AI.\n\nThe example projects are another great resource for seeing real-world usage of these tools.\n\n## Compatibility\nSwift AI currently depends on Apple's [Accelerate](https:\u002F\u002Fdeveloper.apple.com\u002Flibrary\u002Fmac\u002Fdocumentation\u002FAccelerate\u002FReference\u002FAccelerateFWRef\u002F) framework for vector\u002Fmatrix calculations and digital signal processing.\n\nIn order to provide support for more platforms, alternative BLAS solutions are being considered.\n\n## Contributing\nContributions to the project are welcome. We simply ask that you strive to maintain consistency with the structure and formatting of existing code.\n\n## Contact\n[Collin Hundley](https:\u002F\u002Fgithub.com\u002Fcollinhundley) is the author and maintainer of Swift AI. Feel free contact him directly via [email](mailto:collinhundley@gmail.com).\n\nIf you have a question about this library or are looking for guidance, we recommend [opening an issue](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002Fnew) so a member of the community can help!\n\n## Consulting\nIf you're looking for for help with deep learning, computer vision, signal processing or other AI applications, you've come to the right place! Contact [Collin](https:\u002F\u002Fgithub.com\u002Fcollinhundley) for more information about consulting\u002Fcontracting.\n\n## Donating\nYour donation to Swift AI will help us continue building excellent open-source tools. All contributions are appreciated!\n\n[![Donate](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSwift-AI_Swift-AI_readme_d9a618d0aa38.png)](https:\u002F\u002Fwww.paypal.com\u002Fcgi-bin\u002Fwebscr?cmd=_donations&business=3FCBZ7MXZJFG2&lc=US&item_name=Swift%20AI&currency_code=USD&bn=PP%2dDonationsBF%3aDonateButton%2epng%3fraw%3dtrue%3aNonHosted)\n","![横幅](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSwift-AI_Swift-AI_readme_872cb7ffa7db.png)\n\nSwift AI 是一款完全用 Swift 编写的高性能深度学习库。我们目前支持所有 Apple 平台，Linux 支持也将很快推出。\n\n## 工具\nSwift AI 包含一系列用于人工智能和科学应用的常用工具：\n\n - [x] [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet)\n    * 一种灵活的全连接神经网络，支持深度学习\n    * 针对 Apple 硬件进行了专门优化，采用先进的并行处理技术\n - [ ] 卷积神经网络\n - [ ] 循环神经网络\n - [ ] 遗传算法库\n - [ ] 快速线性代数库\n - [ ] 信号处理库\n\n## 示例项目\n我们创建了一些示例项目，以展示 Swift AI 的使用方法。每个项目都位于独立的仓库中，几乎无需配置即可构建：\n\n - [NeuralNet-MNIST](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet-MNIST)\n    * 一个针对 [MNIST](http:\u002F\u002Fyann.lecun.com\u002Fexdb\u002Fmnist\u002F) 手写数字数据库的 [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet) 训练示例\n    * 训练神经网络以识别手写数字\n    * 专为 macOS 构建\n - [NeuralNet-Handwriting-iOS](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet-Handwriting-iOS)\n    * 使用 [NeuralNet](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet) 进行手写识别的演示\n    * 已经预训练；只需下载并运行\n    * 专为 iOS 构建\n\n## 使用方法\n每个模块现在都包含自己的文档。我们建议您仔细阅读文档，以获取有关如何使用 Swift AI 各个组件的详细说明。\n\n示例项目也是了解这些工具实际应用的绝佳资源。\n\n## 兼容性\nSwift AI 目前依赖于 Apple 的 [Accelerate](https:\u002F\u002Fdeveloper.apple.com\u002Flibrary\u002Fmac\u002Fdocumentation\u002FAccelerate\u002FReference\u002FAccelerateFWRef\u002F) 框架来进行向量\u002F矩阵计算和数字信号处理。\n\n为了支持更多平台，我们正在考虑采用其他 BLAS 解决方案。\n\n## 贡献\n欢迎为本项目做出贡献。我们只要求您努力保持与现有代码结构和格式的一致性。\n\n## 联系方式\n[Collin Hundley](https:\u002F\u002Fgithub.com\u002Fcollinhundley) 是 Swift AI 的作者和维护者。您可以通过 [电子邮件](mailto:collinhundley@gmail.com) 直接联系他。\n\n如果您对本库有任何疑问或需要指导，我们建议您 [提交一个问题](https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002Fnew)，以便社区成员为您提供帮助！\n\n## 咨询服务\n如果您需要深度学习、计算机视觉、信号处理或其他人工智能应用方面的帮助，您来对地方了！请通过 [Collin](https:\u002F\u002Fgithub.com\u002Fcollinhundley) 获取更多关于咨询\u002F合同服务的信息。\n\n## 捐赠\n您的捐赠将帮助 Swift AI 继续开发优秀的开源工具。我们非常感谢所有捐助！\n\n[![捐赠](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSwift-AI_Swift-AI_readme_d9a618d0aa38.png)](https:\u002F\u002Fwww.paypal.com\u002Fcgi-bin\u002Fwebscr?cmd=_donations&business=3FCBZ7MXZJFG2&lc=US&item_name=Swift%20AI&currency_code=USD&bn=PP%2dDonationsBF%3aDonateButton%2epng%3fraw%3dtrue%3aNonHosted)","# Swift-AI 快速上手指南\n\n## 环境准备\n- 系统要求：macOS 10.15+ 或 iOS 13+\n- 前置依赖：Xcode 12.5+ 及命令行工具（运行 `xcode-select --install`）\n\n## 安装步骤\n1. 在 Xcode 中创建新项目或打开现有项目  \n2. 选择 **File > Add Packages...**  \n3. 输入仓库地址：`https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FNeuralNet.git`  \n   （网络较慢时可尝试镜像地址：`https:\u002F\u002Fhub.fastgit.org\u002FSwift-AI\u002FNeuralNet.git`）  \n4. 选择版本范围（如 `1.0.0` 以上），点击 **Add Package**  \n5. 确保勾选目标项目，完成添加  \n\n## 基本使用\n```swift\nimport NeuralNet\n\n\u002F\u002F 创建全连接神经网络（输入784，隐藏层128，输出10）\nlet net = NeuralNet(layers: [784, 128, 10])\n\n\u002F\u002F 生成随机输入数据\nlet input = Tensor\u003CFloat>(repeating: 0.0, shape: [784])\n\n\u002F\u002F 前向传播\nlet output = net.forward(input)\n\nprint(output)\n```","一位医疗应用开发者正在为老年人设计iOS手写处方识别工具，帮助他们快速解读模糊的医生手写内容。  \n\n### 没有 Swift-AI 时  \n- 手动编写神经网络代码耗时且易错，开发周期长达数周，频繁调试导致项目延期。  \n- 在iPhone上运行时识别延迟高，用户等待3秒以上，操作卡顿体验差。  \n- 需集成TensorFlow等外部库，应用体积膨胀至150MB，安装困难且占用存储空间大。  \n- 缺乏硬件优化，后台运行时电池消耗快，单次使用耗电15%，影响设备续航。  \n\n### 使用 Swift-AI 后  \n- 直接调用NeuralNet模块加载预训练模型，仅需10行代码，开发时间缩短至3天，代码简洁易维护。  \n- 识别速度提升50%，实时反馈（0.5秒内完成），用户滑动书写时流畅无卡顿。  \n- 轻量级集成，应用体积压缩至100MB，安装包更小，分发效率提升40%。  \n- 高效利用Apple Accelerate框架，电池续航延长20%，单次使用仅耗电12%，提升长期使用体验。  \n\nSwift-AI让开发者快速构建高效、低功耗的AI应用，无缝融入Apple生态，显著提升开发效率和终端用户体验。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSwift-AI_Swift-AI_ac523121.png","Swift AI","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FSwift-AI_35595f90.png","The Swift machine learning library",null,"https:\u002F\u002Fgithub.com\u002FSwift-AI",[81],{"name":82,"color":83,"percentage":84},"Swift","#F05138",100,6068,554,"2026-04-04T21:21:52","MIT","macOS","未说明",{"notes":92,"python":93,"dependencies":94},"需安装Xcode及Swift工具链，仅支持macOS和iOS，Linux支持正在开发中，依赖Apple Accelerate框架","不需要",[],[14,13],[97,98,99,100,101,102,103],"swift","machine-learning","deep-learning","artificial-intelligence","ios","macos","ocr","2026-03-27T02:49:30.150509","2026-04-06T05:16:45.867032",[107,112,117,122,127,132],{"id":108,"question_zh":109,"answer_zh":110,"source_url":111},8906,"如何解决 'Module file was created by an older version of the compiler' 错误？","更新代码到最新master分支，或使用Xcode 7.3进行构建。维护者已推送更新到master，具体请参考：https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F40","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F40",{"id":113,"question_zh":114,"answer_zh":115,"source_url":116},8907,"如何理解训练代码中的输入和反向传播步骤？","这是训练阶段的代码。x值从-5到5范围生成（计算公式：(-500 + (Float(index) * 1000) \u002F Float(self.numPoints)) \u002F 100）。网络通过update(inputs: [x])更新，sineFunc(x)获取目标值，然后backpropagate(answer: [answer])反向传播误差。预测在computePoints()函数中实现，其中使用network.update(inputs: [x])获取预测值。","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F44",{"id":118,"question_zh":119,"answer_zh":120,"source_url":121},8908,"如何将Storage分离到单独文件？","维护者已合并PR #17，将Storage扩展移到单独文件Storage.swift。具体操作：将FFNN.swift中相关代码移动到Storage.swift。参考PR: https:\u002F\u002Fgithub.com\u002Fcollinhundley\u002FSwift-AI\u002Fpull\u002F17","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F16",{"id":123,"question_zh":124,"answer_zh":125,"source_url":126},8909,"如何为Swift AI项目贡献代码？","提交Pull Request，维护者会审核。如果有大量贡献，可以申请成为协作者。具体：'If you have new changes to add now, go ahead and submit a PR and I'll take a look at it.' 或 'If you have lots of contributions that you'd like to make, I'm not opposed to adding more collaborators if that's easier.'","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F25",{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},8910,"Swift AI中RNN实现的进展如何？","目前没有直接RNN实现，但可以使用Swift-AI的FNN进行训练。参考Swift-HAR项目（https:\u002F\u002Fgithub.com\u002FSapphirine\u002FSwift-HAR）用于iOS训练和分类。讨论已转移到issue #50。","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F50",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},8911,"RNN实现是否在进行中？","讨论已转移到issue #50，请参考该issue获取最新进展。","https:\u002F\u002Fgithub.com\u002FSwift-AI\u002FSwift-AI\u002Fissues\u002F34",[138,143],{"id":139,"version":140,"summary_zh":141,"released_at":142},106325,"2.0.0","#### Swift AI has been completely rewritten for Swift 3.1!\r\n\r\nThis update brings many changes, so I'd like to note a few of the biggest ones here:\r\n - Swift 3.1 language support\r\n - Swift Package Manager support\r\n - Significant API improvements and syntactical changes\r\n - Support for custom activation functions and cost functions!\r\n - Persistent storage now uses plaintext JSON for easy readability and cross-platform support\r\n - `FFNN` has been renamed to `NeuralNet`\r\n - Various performance improvements\r\n\r\nWe've also removed some components from this repository. Namely:\r\n - Example projects\r\n - Vector\u002Fmatrix library\r\n - Random number generator\r\n\r\nThe reason for removing these components is simple: in accordance with its SPM support, Swift AI is intended to be modular and expandable.  Importing a neural network should not require you to import an entire collection of documentation and iOS example projects ;)\r\n\r\nThis is just Phase 1 of a series of changes that are planned for Swift AI. For the time being, the `NeuralNet` module will remain here in the top-level repository - but the ultimate goal is to create a GitHub organization account and continue expanding the library with new tools in their own individual packages.\r\n\r\nThank you for all your support and contributions!\r\n","2017-04-05T00:55:20",{"id":144,"version":145,"summary_zh":146,"released_at":147},106326,"1.0.0","v1.0 is the official Swift 2.2 release of Swift AI.  This release is pre-Swift Package Manager and includes the example projects bundled in the main repo. \n\nAll future versions will be built for Swift 3 with SPM support.\n","2016-11-30T19:13:08"]