| Event Type | Date | Description | Course Materials |
|---|---|---|---|
| Lecture 1 | Tuesday April 4 |
Course Introduction Computer vision overview Historical context Course logistics |
[slides] [video] |
| Lecture 2 | Thursday April 6 |
Image Classification The data-driven approach K-nearest neighbor Linear classification I |
[slides]
[video]
[python/numpy tutorial] [image classification notes] [linear classification notes] |
| Lecture 3 | Tuesday April 11 |
Loss Functions and Optimization Linear classification II Higher-level representations, image features Optimization, stochastic gradient descent |
[slides]
[video]
[linear classification notes] [optimization notes] |
| Lecture 4 | Thursday April 13 |
Introduction to Neural Networks Backpropagation Multi-layer Perceptrons The neural viewpoint |
[slides]
[video]
[backprop notes] [linear backprop example] [derivatives notes] (optional) [Efficient BackProp] (optional) related: [1], [2], [3] (optional) |
| Lecture 5 | Tuesday April 18 |
Convolutional Neural Networks History Convolution and pooling ConvNets outside vision |
[slides]
[video]
ConvNet notes |
| Lecture 6 | Thursday April 20 |
Training Neural Networks, part I Activation functions, initialization, dropout, batch normalization |
[slides]
[video]
Neural Nets notes 1 Neural Nets notes 2 Neural Nets notes 3 tips/tricks: [1], [2], [3] (optional) Deep Learning [Nature] (optional) |
| A1 Due | Thursday April 20 |
Assignment #1 due kNN, SVM, SoftMax, two-layer network |
[Assignment #1] |
| Lecture 7 | Tuesday April 25 |
Training Neural Networks, part II Update rules, ensembles, data augmentation, transfer learning |
[slides]
[video]
Neural Nets notes 3 |
| Proposal due | Tuesday April 25 |
Couse Project Proposal due | [proposal description] |
| Lecture 8 | Thursday April 27 |
Deep Learning Software Caffe, Torch, Theano, TensorFlow, Keras, PyTorch, etc |
[slides] [video] |
| Lecture 9 | Tuesday May 2 |
CNN Architectures AlexNet, VGG, GoogLeNet, ResNet, etc |
[slides]
[video]
AlexNet, VGGNet, GoogLeNet, ResNet |
| Lecture 10 | Thursday May 4 |
Recurrent Neural Networks RNN, LSTM, GRU Language modeling Image captioning, visual question answering Soft attention |
[slides]
[video]
DL book RNN chapter (optional) min-char-rnn, char-rnn, neuraltalk2 |
| A2 Due | Thursday May 4 |
Assignment #2 due Neural networks, ConvNets |
[Assignment #2] |
| Midterm | Tuesday May 9 |
In-class midterm Location: Various (not our usual classroom) |
|
| Lecture 11 | Thursday May 11 |
Detection and Segmentation Semantic segmentation Object detection Instance segmentation |
[slides]
[video]
|
| Lecture 12 | Tuesday May 16 |
Visualizing and Understanding Feature visualization and inversion Adversarial examples DeepDream and style transfer |
[slides]
[video]
DeepDream neural-style fast-neural-style |
| Milestone | Tuesday May 16 |
Course Project Milestone due | |
| Lecture 13 | Thursday May 18 |
Generative Models PixelRNN/CNN Variational Autoencoders Generative Adversarial Networks |
[slides]
[video]
|
| Lecture 14 | Tuesday May 23 |
Deep Reinforcement Learning Policy gradients, hard attention Q-Learning, Actor-Critic |
[slides]
[video]
|
| Guest Lecture | Thursday May 25 |
Invited Talk: Song Han
Efficient Methods and Hardware for Deep Learning |
[slides]
[video]
|
| A3 Due | Friday May 26 |
Assignment #3 due | [Assignment #3] |
| Guest Lecture | Tuesday May 30 |
Invited Talk: Ian Goodfellow
Adversarial Examples and Adversarial Training |
[slides]
[video]
|
| Lecture 16 | Thursday June 1 |
Student spotlight talks, conclusions | [slides] |
| Poster Due | Monday June 5 |
Poster PDF due | [poster description] |
| Poster Presentation | Tuesday June 6 |
||
| Final Project Due | Monday June 12 |
Final course project due date | [reports] |