参考网站http://www.educg.net.cn/resources.html

https://github.com/ZuzooVn/machine-learning-for-software-engineers/blob/master/README-zh-CN.md

https://github.com/rasbt/deeplearning-models

https://github.com/jupyter/jupyter/wiki/A-gallery-of-interesting-Jupyter-Notebooks

https://www.oracle.com/database/technologies/bigdatalite-v411.html

一、ipython-notebooks

This repo contains various IPython notebooks I\’ve created to experiment with libraries and work through exercises, and explore subjects that I find interesting. I\’ve included notebook viewer links below. Click the link to see a live rendering of the notebook.

Language

These notebooks contain introductory content such as an overview of the language and a review of IPython\’s functionality.

Introduction To Python
IPython Magic Commands

Libraries

Examples using a variety of popular “data science” Python libraries.

NumPy
SciPy
Matplotlib
Pandas
Statsmodels
Scikit-learn
Seaborn
NetworkX
PyMC
NLTK
DEAP
Gensim

Machine Learning Exercises

Implementations of the exercises presented in Andrew Ng\’s “Machine Learning” class on Coursera.

Exercise 1 – Linear Regression
Exercise 2 – Logistic Regression
Exercise 3 – Multi-Class Classification
Exercise 4 – Neural Networks
Exercise 6 – Support Vector Machines
Exercise 7 – K-Means Clustering & PCA
Exercise 8 – Anomaly Detection & Recommendation Systems

Tensorflow Deep Learning Exercises

Implementations of the assignments from Google\’s Udacity course on deep learning.

Assignment 1 – Intro & Data Prep
Assignment 2 – Regression & Neural Nets
Assignment 3 – Regularization
Assignment 4 – Convolutions
Assignment 5 – Word Embeddings
Assignment 6 – Recurrent Nets

Spark Big Data Labs

Lab exercises for the original Spark classes on edX.

Lab 0 – Learning Apache Spark
Lab 1 – Building A Word Count Application
Lab 2 – Web Server Log Analysis
Lab 3 – Text Analysis & Entity Resolution
Lab 4 – Introduction To Machine Learning
ML Lab 3 – Linear Regression
ML Lab 4 – Click-Through Rate Prediction
ML Lab 5 – Principal Component Analysis

Fast.ai Lessons

Notebooks from Jeremy Howard\’s fast.ai class.

Lesson 1 – Image Classification
Lesson 2 – Multi-label Classification
Lesson 3 – Structured And Time Series Data
Lesson 4 – Sentiment Classification
Lesson 5 – Recommendation Using Deep Learning
Lesson 6 – Language Modeling With RNNs
Lesson 7 – Convolutional Networks In Detail

Deep Learning With Keras

Notebooks using Keras to implement deep learning models.

Part 1 – Structured And Time Series Data
Part 2 – Convolutional Networks
Part 3 – Recommender Systems
Part 4 – Recurrent Networks
Part 5 – Anomaly Detection
Part 6 – Generative Adversarial Networks

Misc

Notebooks covering various interesting topics!

Comparison Of Various Code Optimization Methods
A Simple Time Series Analysis of the S&P 500 Index
An Intro To Probablistic Programming
Language Exploration Using Vector Space Models
Solving Problems With Dynamic Programming
Time Series Forecasting With Prophet
Markov Chains From Scratch
A Sampling Of Monte Carlo Methods

 

二、Deep Learning Models

A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.

Traditional Machine Learning

  • Perceptron
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Logistic Regression
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Softmax Regression (Multinomial Logistic Regression)
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Softmax Regression with MLxtend\’s plot_decision_regions on Iris
       [PyTorch: GitHub | Nbviewer]

Multilayer Perceptrons

  • Multilayer Perceptron
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Multilayer Perceptron with Dropout
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Multilayer Perceptron with Batch Normalization
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Multilayer Perceptron with Backpropagation from Scratch
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

Convolutional Neural Networks

Basic

  • Convolutional Neural Network
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Neural Network with He Initialization
       [PyTorch: GitHub | Nbviewer]

Concepts

  • Replacing Fully-Connnected by Equivalent Convolutional Layers
       [PyTorch: GitHub | Nbviewer]

Fully Convolutional

  • Fully Convolutional Neural Network
       [PyTorch: GitHub | Nbviewer]

LeNet

  • LeNet-5 on MNIST
       [PyTorch: GitHub | Nbviewer]

  • LeNet-5 on CIFAR-10
       [PyTorch: GitHub | Nbviewer]

  • LeNet-5 on QuickDraw
       [PyTorch: GitHub | Nbviewer]

AlexNet

  • AlexNet on CIFAR-10
       [PyTorch: GitHub | Nbviewer]

VGG

  • Convolutional Neural Network VGG-16
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • VGG-16 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • VGG-16 Dogs vs Cats Classifier
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Neural Network VGG-19
       [PyTorch: GitHub | Nbviewer]

DenseNet

  • DenseNet-121 Digit Classifier Trained on MNIST
       [PyTorch: GitHub | Nbviewer]

  • DenseNet-121 Image Classifier Trained on CIFAR-10
       [PyTorch: GitHub | Nbviewer]

ResNet

  • ResNet and Residual Blocks
       [PyTorch: GitHub | Nbviewer]

  • ResNet-18 Digit Classifier Trained on MNIST
       [PyTorch: GitHub | Nbviewer]

  • ResNet-18 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • ResNet-34 Digit Classifier Trained on MNIST
       [PyTorch: GitHub | Nbviewer]

  • ResNet-34 Object Classifier Trained on QuickDraw
       [PyTorch: GitHub | Nbviewer]

  • ResNet-34 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • ResNet-50 Digit Classifier Trained on MNIST
       [PyTorch: GitHub | Nbviewer]

  • ResNet-50 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • ResNet-101 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • ResNet-101 Trained on CIFAR-10
       [PyTorch: GitHub | Nbviewer]

  • ResNet-152 Gender Classifier Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

Network in Network

  • Network in Network CIFAR-10 Classifier
       [PyTorch: GitHub | Nbviewer]

Normalization Layers

  • BatchNorm before and after Activation for Network-in-Network CIFAR-10 Classifier
       [PyTorch: GitHub | Nbviewer]

  • Filter Response Normalization for Network-in-Network CIFAR-10 Classifier
       [PyTorch: GitHub | Nbviewer]

Metric Learning

  • Siamese Network with Multilayer Perceptrons
       [TensorFlow 1: GitHub | Nbviewer]

Autoencoders

Fully-connected Autoencoders

  • Autoencoder (MNIST)
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Autoencoder (MNIST) + Scikit-Learn Random Forest Classifier
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

Convolutional Autoencoders

  • Convolutional Autoencoder with Deconvolutions / Transposed Convolutions
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Autoencoder with Deconvolutions and Continuous Jaccard Distance
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Autoencoder with Deconvolutions (without pooling operations)
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Autoencoder with Nearest-neighbor Interpolation
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Autoencoder with Nearest-neighbor Interpolation — Trained on CelebA
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Autoencoder with Nearest-neighbor Interpolation — Trained on Quickdraw
       [PyTorch: GitHub | Nbviewer]

Variational Autoencoders

  • Variational Autoencoder
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Variational Autoencoder
       [PyTorch: GitHub | Nbviewer]

Conditional Variational Autoencoders

  • Conditional Variational Autoencoder (with labels in reconstruction loss)
       [PyTorch: GitHub | Nbviewer]

  • Conditional Variational Autoencoder (without labels in reconstruction loss)
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Conditional Variational Autoencoder (with labels in reconstruction loss)
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Conditional Variational Autoencoder (without labels in reconstruction loss)
       [PyTorch: GitHub | Nbviewer]

Generative Adversarial Networks (GANs)

  • Fully Connected GAN on MNIST
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Fully Connected Wasserstein GAN on MNIST
       [PyTorch: GitHub | Nbviewer]

  • Convolutional GAN on MNIST
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Convolutional GAN on MNIST with Label Smoothing
       [TensorFlow 1: GitHub | Nbviewer]
       [PyTorch: GitHub | Nbviewer]

  • Convolutional Wasserstein GAN on MNIST
       [PyTorch: GitHub | Nbviewer]

  • “Deep Convolutional GAN” (DCGAN) on Cats and Dogs Images
       [PyTorch: GitHub | Nbviewer]

  • “Deep Convolutional GAN” (DCGAN) on CelebA Face Images
       [PyTorch: GitHub | Nbviewer]

Graph Neural Networks (GNNs)

  • Most Basic Graph Neural Network with Gaussian Filter on MNIST
       [PyTorch: GitHub | Nbviewer]

  • Basic Graph Neural Network with Edge Prediction on MNIST
       [PyTorch: GitHub | Nbviewer]

  • Basic Graph Neural Network with Spectral Graph Convolution on MNIST
       [PyTorch: GitHub | Nbviewer]

Recurrent Neural Networks (RNNs)

Many-to-one: Sentiment Analysis / Classification

  • A simple single-layer RNN (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • A simple single-layer RNN with packed sequences to ignore padding characters (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • RNN with LSTM cells (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • RNN with LSTM cells (IMDB) and pre-trained GloVe word vectors
       [PyTorch: GitHub | Nbviewer]

  • RNN with LSTM cells and Own Dataset in CSV Format (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • RNN with GRU cells (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • Multilayer bi-directional RNN (IMDB)
       [PyTorch: GitHub | Nbviewer]

  • Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (AG News)
       [PyTorch: GitHub | Nbviewer]

  • Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (Yelp Review Polarity)
       [PyTorch: GitHub | Nbviewer]

  • Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (Amazon Review Polarity)
       [PyTorch: GitHub | Nbviewer]

Many-to-Many / Sequence-to-Sequence

  • A simple character RNN to generate new text (Charles Dickens)
       [PyTorch: GitHub | Nbviewer]

Ordinal Regression

  • Ordinal Regression CNN — CORAL w. ResNet34 on AFAD-Lite
       [PyTorch: GitHub | Nbviewer]

  • Ordinal Regression CNN — Niu et al. 2016 w. ResNet34 on AFAD-Lite
       [PyTorch: GitHub | Nbviewer]

  • Ordinal Regression CNN — Beckham and Pal 2016 w. ResNet34 on AFAD-Lite
       [PyTorch: GitHub | Nbviewer]

Tips and Tricks

  • Cyclical Learning Rate
       [PyTorch: GitHub | Nbviewer]

  • Annealing with Increasing the Batch Size (w. CIFAR-10 & AlexNet)
       [PyTorch: GitHub | Nbviewer]

  • Gradient Clipping (w. MLP on MNIST)
       [PyTorch: GitHub | Nbviewer]

Transfer Learning

  • Transfer Learning Example (VGG16 pre-trained on ImageNet for Cifar-10)
       [PyTorch: GitHub | Nbviewer]

Visualization and Interpretation

  • Vanilla Loss Gradient (wrt Inputs) Visualization (Based on a VGG16 Convolutional Neural Network for Kaggle\’s Cats and Dogs Images)
       [PyTorch: GitHub | Nbviewer]

  • Guided Backpropagation (Based on a VGG16 Convolutional Neural Network for Kaggle\’s Cats and Dogs Images)
       [PyTorch: GitHub | Nbviewer]

PyTorch Workflows and Mechanics

Custom Datasets

  • Custom Data Loader Example for PNG Files
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — CSV files converted to HDF5
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Face Images from CelebA
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Drawings from Quickdraw
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Drawings from the Street View House Number (SVHN) Dataset
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Asian Face Dataset (AFAD)
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Dating Historical Color Images
       [PyTorch: GitHub | Nbviewer]

  • Using PyTorch Dataset Loading Utilities for Custom Datasets — Fashion MNIST
       [PyTorch: GitHub | Nbviewer]

Training and Preprocessing

  • Generating Validation Set Splits
       [PyTorch: GitHub | Nbviewer]

  • Dataloading with Pinned Memory
       [PyTorch: GitHub | Nbviewer]

  • Standardizing Images
       [PyTorch: GitHub | Nbviewer]

  • Image Transformation Examples
       [PyTorch: GitHub | Nbviewer]

  • Char-RNN with Own Text File
       [PyTorch: GitHub | Nbviewer]

  • Sentiment Classification RNN with Own CSV File
       [PyTorch: GitHub | Nbviewer]

Parallel Computing

  • Using Multiple GPUs with DataParallel — VGG-16 Gender Classifier on CelebA
       [PyTorch: GitHub | Nbviewer]

Other

  • Sequential API and hooks
       [PyTorch: GitHub | Nbviewer]

  • Weight Sharing Within a Layer
       [PyTorch: GitHub | Nbviewer]

  • Plotting Live Training Performance in Jupyter Notebooks with just Matplotlib
       [PyTorch: GitHub | Nbviewer]

Autograd

  • Getting Gradients of an Intermediate Variable in PyTorch
       [PyTorch: GitHub | Nbviewer]

TensorFlow Workflows and Mechanics

Custom Datasets

  • Chunking an Image Dataset for Minibatch Training using NumPy NPZ Archives
       [TensorFlow 1: GitHub | Nbviewer]

  • Storing an Image Dataset for Minibatch Training using HDF5
       [TensorFlow 1: GitHub | Nbviewer]

  • Using Input Pipelines to Read Data from TFRecords Files
       [TensorFlow 1: GitHub | Nbviewer]

  • Using Queue Runners to Feed Images Directly from Disk
       [TensorFlow 1: GitHub | Nbviewer]

  • Using TensorFlow\’s Dataset API
       [TensorFlow 1: GitHub | Nbviewer]

Training and Preprocessing

  • Saving and Loading Trained Models — from TensorFlow Checkpoint Files and NumPy NPZ Archives
       [TensorFlow 1: GitHub | Nbviewer]

 

三、机器学习资源大全

预备知识

这个小章节是一些在每日计划开始前我想去了解的一些预备知识与一些有趣的信息。

  •  Data Analytics，Data Analysis，数据挖掘，数据科学，机器学习，大数据的区别是什么？

  •  学习如何去学习

  •  不要斩断锁链

  •  如何自学

每日计划

每个主题都不需要用一整天来完全理解它们，你可以每天完成它们中的多个。

每天我都会从下面的列表中选一个出来，一遍又一遍的读，做笔记，练习，用Python或R语言实现它。

动机

  •  梦

机器学习概论

  •  形象的机器学习简介

  •  一份温柔的机器学习指南

  •  为开发者准备的机器学习简介

  •  菜鸟的机器学习基础

  •  你如何向非计算机专业的人来解释机器学习与数据挖掘？

  •  在罩子下的机器学习，博文简单明了地介绍了机器学习的原理

  •  机器学习是什么？它是如何工作的呢？

  •  深度学习——一份非技术性的简介

掌握机器学习

  •  掌握机器学习的方法

  •  程序员的机器学习

  •  掌握并运用机器学习

  •  Python机器学习小课程

  •  机器学习算法小课程

有趣的机器学习

  •  机器学习真有趣！

  •  Part 2: 使用机器学习来创造超级马里奥的关卡

  •  Part 3: 深度学习与卷积神经网络

  •  Part 4: 现代人脸识别与深度学习

  •  Part 5: 翻译与深度学习和序列的魔力

  •  Part 6: 如何使用深度学习进行语音识别

  •  Part 7: 使用生成式对抗网络创造 8 像素艺术

  •  Part 8: 如何故意欺骗神经网络

机器学习简介(用手指沾上墨水来书写机器学习简介)

  •  Part 1 : 什么是机器学习？

  •  Part 2 : 监督学习与非监督学习

一本深入的机器学习指南

  •  概述，目标，学习类型和算法

  •  数据的选择，准备与建模

  •  模型的评估，验证，复杂性与改进

  •  模型性能与误差分析

  •  无监督学习，相关领域与实践中的机器学习

故事与经验

  •  一周的机器学习

  •  一年的机器学习

  •  我是如何在3天内写出我的第一个机器学习程序的

  •  学习路径：你成为机器学习专家的导师

  •  不是PhD你也可以成为机器学习的摇滚明星

  •  如何6个月成为一名数据科学家：一名黑客的职业规划

    • 视频

    • 幻灯片

  •  5个你成为机器学习工程师必须要掌握的技能

  •  你是一个自学成才的机器学习工程师吗？你是怎么做的？花了多长时间？

  •  一个人如何成为一名优秀的机器学习工程师？

  •  一个专注于机器学习的学术假期

机器学习算法

  •  用“士兵”来表示10种机器学习算法

  •  Top10的数据挖掘算法

  •  介绍10种机器学习的术语

  •  机器学习算法之旅

  •  机器学习工程师需要知道的10种算法

  •  比较监督学习算法

  • 收集的最简化、可执行的机器学习算法

入门书籍

  •  《Data Smart: Using Data Science to Transform Information into Insight》第 1 版

  •  《Data Science for Business: What you need to know about data mining and data analytic-thinking》

  •  《Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die》

实用书籍

  •  Hacker 的机器学习

    • GitHub repository(R)

    • GitHub repository(Python)

  •  Python 机器学习

    • GitHub repository

  •  集体智慧编程: 创建智能 Web 2.0 应用

  •  机器学习: 算法视角，第二版

    • GitHub repository

    • Resource repository

  •  Python 机器学习简介: 数据科学家指南

    • GitHub repository

  •  数据挖掘: 机器学习工具与技术实践，第 3 版

    • Teaching material        – 1-5 章幻灯片(zip)        – 6-8 章幻灯片(zip)

  •  Machine Learning in Action

    • GitHub repository

  •  Reactive Machine Learning Systems(MEAP)

    • GitHub repository

  •  An Introduction to Statistical Learning

    • GitHub repository(R)

    • GitHub repository(Python)    – 视频

  •  使用 Python 构建机器学习系统

    • GitHub repository

  •  学习 scikit-learn: 用 Python 进行机器学习

    • GitHub repository

  •  Probabilistic Programming & Bayesian Methods for Hackers

  •  Probabilistic Graphical Models: Principles and Techniques

  •  Machine Learning: Hands-On for Developers and Technical Professionals

    • Machine Learning Hands-On for Developers and Technical Professionals review

    • GitHub repository

  •  从数据中学习    – 在线教程

  •  强化学习——简介(第 2 版)

    • GitHub repository

  •  使用TensorFlow(MEAP)进行机器学习

    • GitHub repository

Kaggle知识竞赛

  •  Kaggle竞赛：怎么样，在哪里开始？

  •  一个初学者如何用一个小项目在机器学习入门并在Kaggle竞争

  •  如何竞争Kaggle的Master

系列视频

  •  Machine Learning for Hackers

  •  Fresh Machine Learning

  •  Josh Gordon 的机器学习菜谱

  •  在 30 分钟以内了解机器学习的一切

  •  一份友好的机器学习简介

  •  Nuts and Bolts of Applying Deep Learning – Andrew Ng

  •  BigML Webinar    – 视频    – 资源

  •  mathematicalmonk\’s Machine Learning tutorials

  •  Machine learning in Python with scikit-learn

    • GitHub repository    – 博客

  •  播放清单 – YouTuBe 上最热门的机器学习、神经网络、深度学习视频

  •  16 个必看的机器学习教程

  •  DeepLearning.TV

  •  Learning To See

  •  神经网络课程 – Université de Sherbrooke

  •  2016年的21个深度学习视频课程

  •  2016年的30个顶级的机器学习与人工智能视频教程 Top Videos, Tutorials & Courses on Machine Learning & Artificial Intelligence from 2016

  •  程序员的深度学习实战

MOOC

  •  edX 的人工智能导论

  •  Udacity的机器学习导论

    • 复习Udacity机器学习导论

  •  Udacity的监督学习、非监督学习及深入

  •  Machine Learning Foundations: A Case Study Approach

  •  Coursera的机器学习

    • 视频

    • 复习Coursera机器学习

    • Coursera的机器学习路线图

  •  机器学习提纯

  •  BigML training

  •  Coursera的神经网络课程

    • 由Geoffrey Hinton（神经网络的先驱）执教

  •  使用TensorFlow创建深度学习应用

  •  描述统计学概论

  •  推理统计学概论

  •  6.S094: 自动驾驶的深度学习

  •  6.S191: 深度学习简介

  •  Coursera 深度学习教程

资源

  •  一个月学会机器学习

  •  一份“非技术性”的机器学习与人工智能指南

  •  Google机器学习工程师最佳实践教程

  •  Hacker News的《软件工程师的机器学习》

  •  开发者的机器学习

  •  为人类

版权声明：本文为xied原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://www.cnblogs.com/xied/p/12710304.html