Schedule and Syllabus
Unless otherwise specified the lectures are Tuesday and Thursday 12pm to 1:20pm in the NVIDIA Auditorium in the Huang Engineering Center. (map)
Discussion sections will (generally) be Fridays 12:30pm to 1:20pm in Gates B03. (map) Check Piazza for any exceptions.
This is the syllabus for the Spring 2019 iteration of the course. The syllabus for the 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 April 2 
Course Introduction Computer vision overview Historical context Course logistics 
[slides] 
Lecture 2  Thursday April 4 
Image Classification The datadriven approach Knearest neighbor Linear classification I 
[slides] [python/numpy tutorial] [image classification notes] [linear classification notes] 
Discussion Section  Friday April 5 
Python / numpy / Google Cloud  [notebook] 
Lecture 3  Tuesday April 9 
Loss Functions and Optimization Linear classification II Higherlevel representations, image features Optimization, stochastic gradient descent 
[slides] [linear classification notes] [optimization notes] 
Lecture 4  Thursday April 11 
Introduction to Neural Networks Backpropagation Multilayer Perceptrons The neural viewpoint 
[slides] [backprop notes] [linear backprop example] [derivatives notes] (optional) [Efficient BackProp] (optional) related: [1], [2], [3] (optional) 
Discussion Section  Friday April 12 
Guidelines for Picking a Project  [slides] 
Lecture 5  Tuesday April 16 
Convolutional Neural Networks History Convolution and pooling ConvNets outside vision 
[slides] ConvNet notes 
A1 Due  Wednesday April 17 
Assignment #1 due kNN, SVM, SoftMax, twolayer network 
[Assignment #1] 
Lecture 6  Thursday April 18 
Deep Learning Hardware and Software CPUs, GPUs, TPUs PyTorch, TensorFlow Dynamic vs Static computation graphs 
[slides] 
Discussion Section  Friday April 19 
Intro to Pytorch and Tensorflow 12:3013:50 at Thornton 102 
[PyTorch notebook] [TensorFlow notebook] [gradio slides] [gradio notebook] 
Lecture 7  Tuesday April 23 
Training Neural Networks, part I  [slides] Neural Nets notes 1 Neural Nets notes 2 Neural Nets notes 3 tips/tricks: [1], [2], [3] (optional) Deep Learning [Nature] (optional) 
Proposal due  Wednesday April 24 
Project Proposal due  [proposal description] 
Lecture 8  Thursday April 25 
Training Neural Networks, part II Update rules, ensembles, data augmentation, transfer learning 
[slides] Neural Nets notes 3 
Discussion Section  Friday April 26 
Backpropagation  
Lecture 9  Tuesday April 30 
CNN Architectures AlexNet, VGG, GoogLeNet, ResNet, etc 
[slides] AlexNet, VGGNet, GoogLeNet, ResNet 
A2 Due  Wednesday May 1 
Assignment #2 due Neural networks, ConvNets 
[Assignment #2] 
Lecture 10  Thursday May 2 
Recurrent Neural Networks RNN, LSTM, GRU Language modeling Image captioning, visual question answering Soft attention 
[slides] DL book RNN chapter (optional) mincharrnn, charrnn, neuraltalk2 
Discussion Section  Friday May 3 
Midterm Review  
Midterm  Tuesday May 7 
Inclass midterm Location: TBA 

Lecture 11  Thursday May 9 
Generative Models  [slides] 
Lecture 12  Tuesday May 14 
Detection and Segmentation  [slides] 
Milestone  Wednesday May 15 
Project Milestone due  
Lecture 13  Thursday May 16 
Visualizing and Understanding Feature visualization and inversion Adversarial examples DeepDream and style transfer 
[slides] DeepDream neuralstyle fastneuralstyle 
Lecture 14  Tuesday May 21 
Deep Reinforcement Learning Policy gradients, hard attention QLearning, ActorCritic 
[slides] 
A3 Due  Wednesday May 22 
Assignment #3 due RNNs, LSTMs, Network Visualization, Style Transfer, GANs 
[Assignment #3] 
Lecture 15 Guest Lecture 
Thursday May 23 
Fairness Accountability Transparency and Ethics in AI With a focus on Computer Vision Timnit Gebru 

Discussion Section  Friday May 24 
Midterm Q&A  
Lecture 16 Guest Lecture 
Tuesday May 28 
Neuroscience and AI Nick Haber 

Lecture 17  Thursday May 30 
HumanCentered AI  [slides] 
Final Project Due  Tuesday June 4 
Project Report due  
Poster Session  Tuesday June 11 
Arrillaga Alumni Center 12:00 pm to 3:30 pm 
本文地址：http://51blog.com/?p=4595
关注我们：请关注一下我们的微信公众号：扫描二维码，公众号：数博联盟
温馨提示：文章内容系作者个人观点，不代表广东高校数据家园_51博客对观点赞同或支持。
版权声明：本文为转载文章，来源于 Standford ，版权归原作者所有，欢迎分享本文，转载请保留出处！
关注我们：请关注一下我们的微信公众号：扫描二维码，公众号：数博联盟
温馨提示：文章内容系作者个人观点，不代表广东高校数据家园_51博客对观点赞同或支持。
版权声明：本文为转载文章，来源于 Standford ，版权归原作者所有，欢迎分享本文，转载请保留出处！