CS231n: Convolutional Neural Networks for Visual Recognition
Schedule and Syllabus
The Spring 2020 iteration of the course will be taught virtually for the entire duration of the quarter. (more information available here )
Unless otherwise speci ed the lectures are Tuesday and Thursday 12pm to 1:20pm.
Discussion sections will (generally) be Fridays 12:30pm to 1:20pm. Check Piazza for any exceptions.
Lectures and discussion sections will be both on Zoom, and they will be recorded for later access from Canvas.
This is the syllabus for the Spring 2020 iteration of the course. The syllabus for the Spring 2019, Spring 2018, Spring 2017, Winter 2016 and Winter 2015 iterations
of this course are still available.
Event Type Date Description Course Materials
Lecture 1 Tuesday Course Introduction
April 7 Computer vision overview
Historical context
Course logistics
Lecture 2 Thursday Image Classi cation
April 9 The data-driven approach
K-nearest neighbor
Linear classi cation I
Discussion Section Friday Python / numpy / Google Cloud
April 10
Lecture 3 Tuesday Loss Functions and Optimization
April 14 Linear classi cation II
Higher-level representations, image features
Optimization, stochastic gradient descent
Lecture 4 Thursday Neural Networks and Backpropagation
April 16 Backpropagation
Multi-layer Perceptrons
The neural viewpoint
Discussion Section Friday Backprop tutorial
April 17
Lecture 5 Tuesday Convolutional Neural Networks
April 21 History
Convolution and pooling
ConvNets outside vision
A1 Due Wednesday Assignment #1 due
April 22 kNN, SVM, SoftMax, two-layer network
Lecture 6 Thursday Deep Learning Hardware and Software
April 23 CPUs, GPUs, TPUs
PyTorch, TensorFlow
Dynamic vs Static computation graphs
Discussion Section Friday Tips and tricks
April 24
Lecture 7 Tuesday Training Neural Networks, part I
April 28
Proposal due Wednesday Project Proposal due
April 29
Lecture 8 Thursday Training Neural Networks, part II
April 30 Update rules, ensembles, data augmentation, transfer learning
Discussion Section Friday Intro to Pytorch and Tensor ow
May 1
Lecture 9 Tuesday CNN Architectures
May 5 AlexNet, VGG, GoogLeNet, ResNet, etc
A2 Due Wednesday Assignment #2 due
May 6 Neural networks, ConvNets
Lecture 10 Thursday Recurrent Neural Networks
May 7 RNN, LSTM, GRU
Language modeling
Image captioning, visual question answering
Soft attention
Discussion Section Friday Midterm Review
May 8
Midterm Tuesday Take-home midterm
May 12
Lecture 11 Thursday Unsupervised Learning
May 14
Discussion Section Friday Detection Software
May 15
Lecture 12 Tuesday Detection and Segmentation
May 19
Milestone Wednesday Project Milestone due
May 20
Lecture 13 Thursday Visualizing and Understanding
May 21 Feature visualization and inversion
Adversarial examples
DeepDream and style transfer
Discussion Section Friday Learning on Videos
May 22
Lecture 14 Tuesday Fairness Accountability Transparency and Ethics in AI
Guest Lecture May 26 Timnit Gebru, Emily Denton
A3 Due Wednesday Assignment #3 due
May 27 RNNs, LSTMs, Network Visualization, Style Transfer, GANs
Lecture 15 Thursday Human-Centered Arti cial Intelligence
May 28 Fei-Fei Li
Lecture 16 Tuesday 3D Vision
Guest Lecture June 2 Hao Su
Lecture 17 Thursday Deep Reinforcement Learning
June 4 Policy gradients, hard attention
Q-Learning, Actor-Critic
Final Project Due Tuesday Project Report + Video Presentation due
June 5
