/dl_tutorials_3rd

Deep learning tutorials (third edition)

MIT LicenseMIT

Deep learning tutorials (third eddition)

Week 1

Introduction to deep learning and tools

Introduction to CNN

  1. ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)

Week 2

Modern CNN

  1. Going Deeper with Convolutions (GoogleLenet)

Monte-Carlo Tree Search with CNN

  1. Mastering the game of Go with deep neural networks and tree search (AlphaGo)

Regularization methods

  1. Dropout- A Simple Way to Prevent Neural Networks from Overfitting
  2. Batch Normalization- Accelerating Deep Network Training by Reducing Internal Covariate Shift

Optimization methods - Momentum, NAG, AdaGrad, AdaDelta, RMSprop, AdaM

  1. ADAM: A Method For Stochastic Optimization
  2. A Practical Guide to Training Restricted Boltzmann Machines (RBM)

Week 3

Semantic segmentation methods

  1. Fully Convolutional Networks for Semantic Segmentation
  2. Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
  3. Learning Deconvolution Network for Semantic Segmentation
  4. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Weakly supervised methods

  1. Learning Deep Features for Discriminative Localization
  2. Is object localization for free? – Weakly-supervised learning with convolutional neural networks

Week 4

Image detection methods

  1. Rich feature hierarchies for accurate object detection and semantic segmentation
  2. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
  3. Fast R-CNN
  4. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  5. You Only Look Once: Unified, Real-Time Object Detection
  6. AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Introduction to RNN and LSTM

Visual Q&A

  1. Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
  2. Multimodal Compact Bilinear Pooling for VQA

Super resolution

  1. Accurate Image Super-Resolution Using Very Deep Convolutional Networks
  2. Deeply-Recursive Convolutional Network for Image Super-Resolution

Deep reinforcement learning

  1. Playing Atari with Deep Reinforcement Learning
  2. Deep Reinforcement Learning with Double Q-learning

Week 5

RNN

  1. Generating Sequences With Recurrent Neural Networks

Word embedding

  1. Distributed Representations of Words and Phrases and their Compositionality

Image captioning

  1. Show and Tell: A Neural Image Caption Generator
  2. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Week 6

Residual network and analyses

  1. Deep Residual Learning for Image Recognition
  2. Residual Networks are Exponential Ensembles of Relatively Shallow Networks
  3. Wide Residual Networks

Neural Styles

  1. Texture Synthesis Using Convolutional Neural Networks
  2. Understanding Deep Image Representations by Inverting Them
  3. A Neural Algorithm of Artistic Style

Bayesian optimization

  1. Practical Bayesian Optimization of Machine Learning Algorithms

Generative adversarial networks

  1. Generative Adversarial Networks
  2. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
  3. Generative Adversarial Text to Image Synthesis
  4. Pixel Level Domain Transfer