Wjh70301/DeepLearning

Deep Learning introduction and its application in various fields

Table of Contents generated with DocToc

• Basic algorithm/Framework
  • Basics Machine learning
  • CNN
  • RNN
  • TensorFlow
  • GBDT
  • SVM
• Applications
  • NLP
  • Search/Rank/CTR
  • Text Classification
  • Recommendations
  • Industrial machine Learning Application design
• Machine learning implementation in large scale system
  • Deep Learning/AI Chip Design
• Reference Materails
  • Kaggle
  • Book
  • Tutorial
  • Courses
  • Workshop
  • Blog
    • Blog Posts
  • Code and Framework
    • Open Source

Basic algorithm/Framework

Basics Machine learning

Basics Machine learning

CNN

CNN

RNN

RNN

TensorFlow

TensorFlow and Keras

GBDT

Tree(decision_tree,xgboost)

SVM

SVM

Applications

NLP

• NLP

Search/Rank/CTR

• Search/Rank/CTR

Text Classification

• Summary of Text Classification

• Convolutional Neural Networks for Sentence Classification. Paper and blog post

• Bidirectional LSTM and one level attentional RNN. blog

Recommendations

• Recommendation using DL

Industrial machine Learning Application design

Industrial machine Learning Application design

Machine learning implementation in large scale system

Machine learning implementation in large scale system

Deep Learning/AI Chip Design

Deep Learning/AI Chip Design

Reference Materails

Kaggle

• Kaggle experience

Book

• Deep Learning: An MIT Press Book
  • By Ian Goodfellow and Yoshua Bengio and Aaron Courville

Tutorial

• Stanford Deep Learning Tutorial

• A Guide to Deep Learning

• Reinforcement Learning- OpenAI Gym

• Fast AI Tutorial

• Introduction to Boosted Trees

Courses

• Stanford: CS231n: Convolutional Neural Networks for Visual Recognition

  • CS231n Chinese Translation

• Berkeley: CS 294: Deep Reinforcement Learning

• MIT: Deep Learning Self Driving Car

• Oxford: Deep Learning on NLP

• UCL: Reinforcement learning (By D.Silver)

• Stanford: CS224n: Natural Language Processing with Deep Learning

• CMU:Scalable Machine Learning (By A. Smola)

Workshop

• Applied Deep Learning Workshop London 2017

• Deep Learning course: lecture slides and lab notebooks

  • Lab 1: Neural Networks and Backpropagation:

    • Intro to MLP with Keras, Numpy and TensorFlow

  • Lab 2: Embeddings and Recommender Systems.

    • Neural Recommender Systems with Explicit Feedback. Neural Recommender Systems with
    • Implicit Feedback and the Triplet Loss

  • Lab 3: Convolutional Neural Networks for Image Classification

  • Convolution and ConvNets with TensorFlow

    • Pretrained ConvNets with Keras
    • Fine Tuning a pretrained ConvNet with Keras (GPU required)

  • Lab 4: Deep Learning for Object Dection and Image Segmentation

    • Fully Convolutional Neural Networks
    • ConvNets for Classification and Localization

  • Lab 5: Text Classification, Word Embeddings and Language Models

  • Text Classification and Word Vectors

    • Character Level Language Model (GPU required)

  • Lab 6: Sequence to Sequence for Machine Translation

Blog

• Simple Reinforcement Learning: Reinforcement Learning With Tensorflow Series(On Medium)

• Deep Reinforcement Learning: Pong from Pixels

• Word2Vec Resource (by Chris McCormick)

• AI, Deep Learning and NLP (By Denny Britz in Google Brain)

Blog Posts

• Understand CNN on NLP

  • IMPLEMENTING A CNN FOR TEXT CLASSIFICATION IN TENSORFLOW

• Understanding RNN

• A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN

• Understanding LSTM Networks and LSTM by Example using Tensorflow

Code and Framework

• LEARNING REINFORCEMENT LEARNING (WITH CODE, EXERCISES AND SOLUTIONS)
  • Github link

Open Source

• Prophet: forecasting at scale by Facebook

Facebook is open sourcing Prophet, a forecasting tool available

some interesting project based on it

1. Forecasting iPad sales using Facebook's Prophet package