ghoshmainak / CS231n

Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition

CS231n Convolutional Neural Networks for Visual Recognition

http://cs231n.stanford.edu/

---

Please make homeworks by your own and look in this repository only when you've already done the assignments. Anyway, it is in your interests if you really want to learn something.

---

Lectures

• #1: Course Introduction / Computer vision overview / Historical context / Course logistics
• #2: Image Classification / The data-driven approach / K-nearest neighbor / Linear classification I
• #3: Loss Functions and Optimization / Linear classification II/ Higher-level representations, image features/ Optimization, stochastic gradient descent
• #4: Introduction to Neural Networks / Backpropagation/ Multi-layer Perceptrons / The neural viewpoint
• #5: Convolutional Neural Networks / History / Convolution and pooling / ConvNets outside vision
• #6: Training Neural Networks, part I / Activation functions, initialization, dropout, batch normalization
• #7: Training Neural Networks, part II / Update rules, ensembles, data augmentation, transfer learning
• #8: Deep Learning Hardware and Software / CPUs, GPUs, TPUs / PyTorch, TensorFlow / Dynamic vs Static computational graphs
• #9: CNN Architectures / AlexNet, VGG, GoogLeNet, ResNet, etc
• #10: Recurrent Neural Networks / RNN, LSTM, GRU / Language modeling / Image captioning, visual question answering / Soft attention
• #11: Detection and Segmentation / Semantic segmentation / Object detection / Instance segmentation
• #12: Generative Models / PixelRNN/CNN / Variational Autoencoders / Generative Adversarial Networks
• #13: Visualizing and Understanding / Feature visualization and inversion / Adversarial examples / DeepDream and style transfer
• #14: Deep Reinforcement Learning / Policy gradients, hard attention / Q-Learning, Actor-Critic

---

Assignment #1: Image Classification, kNN, SVM, Softmax, Neural Network

• Q1: k-Nearest Neighbor classifier
• Q2: Training a Support Vector Machine
• Q3: Implement a Softmax classifier
• Q4: Two-Layer Neural Network
• Q5: Higher Level Representations: Image Features

Assignment #2: Fully-Connected Nets, Batch Normalization, Dropout, Convolutional Nets

• Q1: Fully-connected Neural Network
• Q2: Batch Normalization
• Q3: Dropout
• Q4: Convolutional Networks
• Q5: PyTorch / TensorFlow on CIFAR-10

Assignment #3: Image Captioning with Vanilla RNNs, Image Captioning with LSTMs, Network Visualization, Style Transfer, Generative Adversarial Networks

• Q1: Image Captioning with Vanilla RNNs
• Q2: Image Captioning with LSTMs
• Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images
• Q4: Style Transfer
• Q5: Generative Adversarial Networks

---

Course Notes

• Google Cloud Tutorial
• AWS Tutorial
  
  
• Module 1: Neural Networks
  • Image Classification: Data-driven Approach, k-Nearest Neighbor, train/val/test splits
  • Linear classification: Support Vector Machine, Softmax
  • Optimization: Stochastic Gradient Descent
  • Backpropagation, Intuitions
  • Neural Networks Part 1: Setting up the Architecture
  • Neural Networks Part 2: Setting up the Data and the Loss
  • Neural Networks Part 3: Learning and Evaluation
  • Putting it together: Minimal Neural Network Case Study
• Module 2: Convolutional Neural Networks
  • Convolutional Neural Networks: Architectures, Convolution / Pooling Layers
  • Understanding and Visualizing Convolutional Neural Networks
  • Transfer Learning and Fine-tuning Convolutional Neural Networks