Event Type | Date | Description | Course Materials |
---|---|---|---|
Lecture 1 | July 13 |
Image Classification The data-driven approach K-nearest neighbor Linear classification I |
[slides]
[video]
[python/numpy tutorial] [image classification notes] [linear classification notes] |
Lecture 2 | July 20 |
Loss Functions and Optimization Linear classification II Higher-level representations, image features Optimization, stochastic gradient descent |
[slides]
[video]
[linear classification notes] [optimization notes] |
Lecture 3 | July 27 |
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) |
A1 Due | August 3 |
Assignment #1 due kNN, SVM, SoftMax, two-layer network |
[Assignment #1] | Lecture 4 | August 3 |
Convolutional Neural Networks History Convolution and pooling ConvNets outside vision |
[slides]
[video]
ConvNet notes |
Lecture 5 | August 10 |
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) |
Lecture 6 | August 17 |
Training Neural Networks, part II Update rules, ensembles, data augmentation, transfer learning |
[slides]
[video]
Neural Nets notes 4 |
Presentation | Auguest 17 |
Assignment #1 presentation Speaker: Seunghoon Yoo |
|
Lecture 7 | August 24 |
Deep Learning Hardware and Software CPUs, GPUs, TPUs PyTorch, TensorFlow Dynamic vs Static computational graphs |
[slides] [video] |
A2 Due | August 31 |
Assignment #2 due Neural networks, ConvNets |
[Assignment #2] |
Presentation | September 7 |
Assignment #2 presentation Speaker: Jaemin Jo |