Deep Learning【精选更新】
🔥 New:【近期热点】DeepNude的算法以及通用的Image-to-Image理论与实践研究🔥 New:一文读懂GAN前世今生:Generative Adversarial Networks - The Story So Far🔥 New:如何规划和启动你的ML/DL项目🔥 New:本期新增神经网络与深度学习、ArXiv论文及代码、深度学习速查表及笔试面试精选等内容
一 Python篇
基础环境
📦 Anaconda
开发语言
- 从0到1,Python Web开发的进击之路
- 从0到1,Python异步编程的演进之路
- 国外著名python在线编程学习网站
- 国内Python在线学习网站
- 以撸代码的形式学习Python
🔥 New:Move: A Language With Programmable Resources
实例练习
- 天猫双12爬虫(福利:266万条商品数据免费下载)
- 新浪微博爬虫分享(一天可抓取 1300 万条数据)
- 如何用100行Python代码做出魔性声控游戏“八分音符酱”
- 50行代码爬网页图片一例
🔥 New:Libra -- My First Transaction
爬虫框架
- Scrapy, a fast high-level web crawling & scraping framework for Python.
- admin ui for scrapy/open source scrapinghub
- Visual scraping for Scrapy
- 简单易用的Python爬虫框架
- 数据科学家的完整学习路径(Python版)
二 深度学习篇
📚
深度学习 - 【经典】机器学习必看的5张图 机器学习全景图
🔥 深度学习/机器学习必备速查表 11767 top stars- 神经网络与深度学习导引(吴恩达)
🔥 【入门推荐】10行命令感受机器学习的神奇(0基础小白适用)- 深度学习入门信息汇总-知乎
- 如何用70行Java代码实现深度神经网络算法
- 【经典书籍】Deep Learning Book Chinese Translation
- 驾驭AI:好的数据集是成功的一半 如何迈出第一步
- 快速搭建有趣的人工智能应用 未充分训练的模型
- Google Cloud AutoML初体验 解决人工智能和机器学习的高门槛,降低高使用成本
- 卷积神经网络简介
算法概述
- 机器学习基础算法 (线性回归、容量/过拟合/欠拟合、最大似然估计、偏差和方差、贝叶斯统计、监督学习算法、无监督学习算法、随机梯度下降、正则化等)
- 随机森林算法概述
- BP神经网络算法概述
- 监督机器学习的优化方法:从线性模型到深度学习
- Adam:随机优化的一种方法
- 训练神经网络的5种算法
🎥
在线课程 (推荐Michael Nielsen及吴恩达视频课程,内容深入浅出。其中1是网易免费版,尚无习题,如需要可在链接2注册获取。)
🔥 Michael Nielsen:Neural Networks and Deep Learning🔥 吴恩达给你的人工智能第一课【初学推荐】- Deep Learning Specialization Master Deep Learning, and Break into AI【原版附带习题】
- 斯坦福监督学习课程
- 斯坦福李飞飞-深度学习计算机视觉
- AI轻松学习版(短视频)
📓
研究论文 - Artificial Intelligence(人工智能)
- Computer Vision and Pattern Recognition(计算机视觉和模式识别)
- awesome-deep-learning-papers:The most cited deep learning papers
- Deep Learning papers reading roadmap for anyone
- awesome-deep-learning:A curated list of awesome Deep Learning tutorials, projects and communities.
- Efficient and Robust Automated Machine Learning
- Microsoft COCO: Common Objects in Context
- Speed/accuracy trade-offs for modern convolutional object detectors
GAN
- Image-to-Image Translation with Conditional Adversarial Networks
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- A Style-Based Generator Architecture for Generative Adversarial Networks
- Generating Cats with StyleGAN on AWS SageMaker
TensorFlow
- TF:An open-source software library for Machine Intelligence
- TensorFlow Guide 中文开发手册
- Swift for TensorFlow documentation repository.
- Swift for TensorFlow Design Overview
- Using Swift for TensorFlow
Caffe
Torch
- Torch is a scientific computing framework for machine learning algorithms that puts GPUs first
- Code and data for paper "Deep Photo Style Transfer"
keras
- keras:Deep Learning library for TensorFlow and Theano
- keras-rl:Deep Reinforcement Learning for Keras
- 小白上手第一步:hello world!
- 小白上手进击之:mnist
Deepmind
- DNC/L2L/..(Deepmind开源代码汇总)
- Github Index(Deepmind官方GitHub)
- DNC:A TensorFlow implementation of the Differentiable Neural Computer.
- sonnet:TensorFlow-based neural network library
- lab:A customisable 3D platform for agent-based AI research
- Deepmind org lab page
- L2L PAPER:Learning to learn by gradient descent by gradient descent
- Google is finding ways to make money from Alphabet's DeepMind A.I. technology 应用
📊
训练平台 - ImageNet:image-net:计算机视觉系统识别项目 目前世界上图像识别最大的数据库
- Kaggle:The Home of Data Science & Machine Learning Kaggle helps you learn, work, and play
- AutoML:CLOUD AUTOML ALPHA Train high quality custom machine learning models with minimum effort and machine learning expertise
- CustomVision.AI:Visual Intelligence Made Easy Microsoft Custom Vision Services
- oneclick:Use AI to Build AI The faster and easier way to build high-performing customized AI for those who don't want to become an AI expert.
辅助工具
- ArXiv最新论文及GitHub代码大全 704 leaderboards • 1038 tasks • 831 datasets • 10673 papers with code
- 数据可视化分析工具汇总
- A powerful, interactive charting and visualization library for browser
- Google机器学习可视化工具Facets:从全新角度观察数据
- Apache Superset (incubating) is a modern, enterprise-ready business intelligence web application
- CUDA在线学习
- A distributed tracing system, and APM ( Application Performance Monitoring )
📈
场景应用 - 垃圾邮件/情绪分析/智能客服等:Library for fast text representation and classification.
- 脸部识别:The world's simplest facial recognition api for Python and the command line.
- Android物体识别APP:Fast-RCNN and Scene Recognition using Caffe
- Google物体识别API:Object_Detection_Tensorflow_API
- 对于谷歌开源的TensorFlow Object Detection API视频物体识别系统实现教程
- Facebook AI 负责人:深度学习技术趋势报告(2016) 一文总结历史沿革
笔面精选
三 数学篇
导数/微积分
深度学习精简版
四 产业篇
重大政策
重要进展
产业新闻
- 人工智能:新技术的“双刃剑”
- Five Ways Machine Learning Can Save Your Company From A Security Breach Meltdown
- 全球100家代表性AI公司 **相关
- Facebook Unveils Cryptocurrency Libra as an Alternative to Bitcoin
- Libra:A simple global currency and financial infrastructure that empowers billions of people
🔥
附:TOP深度学习项目 最后更新(star5000+排序): 2019.04.02 / 上次更新:2018.01.27
Project Name | Stars | Description |
---|---|---|
TensorFlow | 124490 | Computation using data flow graphs for scalable machine learning. |
TensorFlow Models | 50630 | Models built with TensorFlow. |
Keras | 39678 | Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow. |
Caffe | 27691 | Caffe: a fast open framework for deep learning. |
TensorFlow Examples | 30458 | TensorFlow tutorials and code examples for beginners. |
Neural Style | 16692 | Torch implementation of neural style algorithm. |
CNTK | 15965 | Computational Network Toolkit (CNTK). |
MXNet | 16622 | Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more. |
Deep Dream | 11871 | Deep Dream. |
OpenAI Gym | 16117 | A toolkit for developing and comparing reinforcement learning algorithms. |
OpenFace | 11845 | Face recognition with deep neural networks. |
ConvNet JS | 9600 | Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser. |
Magenta | 12790 | Magenta: Music and Art Generation with Machine Intelligence |
Roc AlphaGo | 8918 | An independent, student-led replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search" (Nature 529, 484-489, 28 Jan 2016). |
Neural Doodle | 9050 | Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.) |
deeplearning4j | 10560 | Deep Learning for Java, Scala & Clojure on Hadoop, Spark. |
Theano | 8732 | Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation. |
Torch | 8241 | Torch7, Deep Learning Library. |
TFLearn | 9002 | Deep learning library featuring a higher-level API for TensorFlow. |
Char RNN | 9211 | Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. |
TensorFlow Playground | 8015 | Play with neural networks! |
Synaptic | 6463 | architecture-free neural network library for node.js and the browser |
Nupic | 5864 | Numenta Platform for Intelligent Computing: a brain-inspired machine intelligence platform, and biologically accurate neural network based on cortical learning algorithms. |
Leaf | 5389 | Open Machine Intelligence Framework for Hackers. |