Schedule
Lectures will be Mondays and Wednesdays 4:30pm  6pm in 1670 Beyster.
Some lectures have reading drawn from the course notes of Stanford CS 231n, written by Andrej Karpathy.
Some lectures have optional reading from the book Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (GBC for short). The entire text of the book is available for free online so you donâ€™t need to buy a copy.
Since this is the first time this course has been taught at Michigan, the schedule is subject to change as we move through the semester.
Event  Date  Description  Course Materials 

Lecture 1  Wednesday September 4 
Course Introduction
Computer vision overview Historical context Course logistics 
[slides]
[video] [Python tutorial] [GBC Sec 1.2] [GBC Sec 6.6] 
Lecture 2  Monday September 9 
Image Classification
Datadriven approach KNearest Neighbor Hyperparameters Crossvalidation 
[slides]
[video] [231n Image Classification] 
Lecture 3  Wednesday September 11 
Linear Classifiers
Softmax / SVM classifiers L2 regularization 
[slides]
[video] [231n Linear Classification] 
A1 Due  Sunday September 15 
Assignment 1 Due
PyTorch warmup kNN Classifier 
[Assignment 1] 
Lecture 4  Monday September 16 
Optimization
Stochastic Gradient Descent Momentum, AdaGrad, Adam Secondorder optimizers 
[slides]
[video] [CS231n Optimization] [GBC Sec. 8.1 to 8.6] 
Lecture 5  Wednesday September 18 
Neural Networks
Feature transforms Fullyconnected networks Universal approximation Convexity 
[slides]
[video] [231n Neural Networks] [GBC Sec. 6.1 to 6.4] [Nielsen on Universal Approximation] 
Lecture 6  Monday September 23 
Backpropagation
Computational Graphs Backpropagation Matrix multiplication example 
[slides]
[video] [231n Backpropagation] [Olah on Backprop] [Nielsen on Backprop] 
Lecture 7  Wednesday September 25 
Convolutional Networks
Convolution Pooling Batch Normalization 
[slides]
[video] [CS231n ConvNets] [GBC Chapter 9] 
Lecture 8  Monday September 30 
CNN Architectures
AlexNet, VGG, ResNet Size vs Accuracy Grouped and Separable Convolutions Neural Architecture Search 
[slides]
[video] [AlexNet] [VGG] [GoogLeNet] [ResNet] 
A2 Due  Monday September 30 
Assignment 2 Due
Linear classifiers Twolayer network 
[Assignment 2] 
Lecture 9  Wednesday October 2 
Hardware and Software
CPUs, GPUs, TPUs Dynamic vs Static graphs PyTorch, TensorFlow 
[slides]
[video] 
Lecture 10  Monday October 7 
Training Neural Networks I
Activation functions Data preprocessing Weight initialization Data augmentation Regularization (Dropout, etc) 
[slides]
[video] [CS231n Training I] 
Lecture 11  Wednesday October 9 
Training Neural Networks II
Learning rate schedules Hyperparameter optimization Model ensembles Transfer learning Largebatch training 
[slides]
[video] [CS231n Training II] [Karpathy "Recipe for Training"] 
Monday October 14 
No Class
Fall Study Break 

A3 Due  Monday October 14 
Assignment 3 Due
Modular API Convolutional Networks Batch Normalization Autograd 
[Assignment 3] 
Lecture 12  Wednesday October 16 
Recurrent Networks
RNN, LSTM, GRU Language modeling Sequencetosequence Image captioning Visual question answering 
[slides]
[video] [Karpathy "Unreasonable Effectiveness"] 
Midterm  Monday October 21 
Inclass Midterm Exam
Location: Chrysler 220 Time: 4:30pm  6pm 

Lecture 13  Wednesday October 23 
Attention
Multimodal attention SelfAttention Transformers 
[slides]
[video] [Bloem "Transformers from Scratch"] [Alammar "The Illustrated Transformer"] 
Guest Lecture  Monday October 28 
Guest Lecture: Luowei Zhou
Vision and Language 

Guest Lecture  Wednesday October 30 
Guest Lecture: Prof. Atul Prakash
Adversarial attacks 

Lecture 14  Monday November 4 
Visualizing and Understanding
Feature visualization Adversarial examples DeepDream, Style transfer 
[slides]
[video] [Distill "Feature Visualization"] [Distill "Building Blocks of Interpretability"] [DeepDream] [neuralstyle] 
Lecture 15  Wednesday November 6 
Object Detection
Singlestage detectors Twostage detectors 
[slides]
[video] 
Lecture 16  Monday November 11 
Image Segmentation
Semantic segmentation Instance segmentation Keypoint estimation 
[slides]
[video] 
Lecture 17  Wednesday November 13 
3D vision
3D shape representations Depth estimation 3D shape prediction Voxels, Pointclouds, SDFs, Meshes 
[slides]
[video] 
A4 Due  Wednesday November 13 
Assignment 4 Due
RNNs, Attention Visualization, style transfer 
[Assignment 4] 
Lecture 18  Monday November 18 
Videos
Video classification Early / Late fusion 3D CNNs Twostream networks 
[slides]
[video] 
Lecture 19  Wednesday November 20 
Generative Models I
Supervised vs Unsupervised learning Discriminative vs Generative models Autoregressive models Variational Autoencoders 
[slides]
[video] 
Monday November 25 
No class
Thanksgiving break 

Wednesday November 27 
No Class
Thanksgiving break 

Lecture 20  Monday December 2 
Generative Models II
More Variational Autoencoders Generative Adversarial Networks 
[slides]
[video] 
Lecture 21  Wednesday December 4 
Reinforcement Learning
RL problem setup Bellman Equation QLearning Policy Gradient 
[slides]
[video] 
Lecture 22  Monday December 9 
Conclusion
Course recap The future of computer vision 
[slides]
[video] 
A5 due  Monday December 9 
Assignment 5 Due
Object detection 
[Assignment 5] 
A6 due  Tuesday December 17 
Assignment 6 Due
Variational Autoencoders Generative Adversarial Networks 
[Assignment 6] 