CS 342 - Neural networks - Fall 2017

meets
TTh 10am-11am GDC 5.302
Fr 1pm-2pm / 2pm-3pm CBA 4.326

instructor Philipp Krähenbühl ( philkr (at) utexas.edu )
office hours Tue 11am-12pm GDC 4.824
Please only visit during office hours or with appointment (or if I didn’t reply your email after the third try)

TA Thomas Crosley ( crosleythomas (at) utexas.edu )
TA hours Thursdays 11:30am-12:30pm, Desk 1 at the UT CS TA Stations

We will use canvas for questions and homework.

Schedule

class section

Date Topic Slides Corresponding book chapters (optional see below) Notes and due dates
Aug 31 Introduction intro Background: Ch 1-5  
Sep 1 Installing tensorflow and building the first compute graph     HW1 out
Sep 5 Single layer networks slides visualizations    
Sep 7 Stochastic gradient descent slides 5.9 HW1 due 11:59pm solution
Sep 8 Logistic regression and MLP Tutorial   HW2 out
Sep 12 Multi-layer networks and back propagation slides Ch 6  
Sep 14 Loss functions slides   HW2 due 11:59pm solution
Sep 15 Regression vs classification Section Practice Section Master   HW3 out
Sep 19 Activation functions + Initialization slides Ch 6  
Sep 21 Convolutions + Pooling slides 9.1-9.3 HW3 due 11:59pm
Sep 22 ConvNets     HW4 out
Sep 26 Early stopping, weight regularization, dropout   7.1-7.3, 7.8, 7.12  
Sep 28 Augmentation, batch normalization, parameter sharing, ensembles   7.4, 7.9, 7.11 HW4 due 11:59pm
Sep 29 Regularization and normalization     HW5 out
Oct 3 Popular Architectures I: LeNet, AlexNet, VGG      
Oct 5 Popular Architectures II: GoogLeNet, ResNet, DenseNet     HW5 due 11:59pm
Oct 6 ResNets     HW6 out
Oct 10 Object detection      
Oct 12 Segmentation     HW6 due 11:59pm
Oct 13 Fully convolutional networks     HW7 out
Oct 17 Visualization and understanding      
Oct 19 Generative models   20.10, 20.12, 20.13 HW7 due 11:59pm
Oct 20 Upconvolution and deep rendering     HW8 out
Oct 24 Recurrent Network I: RNN, LSTM, GRU   10.1-10.11  
Oct 26 Recurrent Network II: ConvNets for recurrent tasks     HW8 due 11:59pm
Oct 27 Future prediction     HW9 out
Oct 31 Deep Reinforcement Learning I: Q-learning and policy gradients      
Nov 2 Deep Reinforcement Learning II: Actor critic     HW9 due 11:59pm
Nov 3 Acting through future prediction     HW10 out
Nov 7 Deep Reinforcement Learning III: Direct future prediction      
Nov 9 Deep Reinforcement Learning IV: Gradient free optimization     HW10 due 11:59pm
Nov 10 Gradient free optimization     HW11 out
Nov 14 Embedding learning      
Nov 16 Style transfer     HW11 due 11:59pm
Nov 17 Driving in SuperTuxKart     Final project out
Nov 21 Language + best results of HW11      
Nov 23 no class      
Nov 24 no class      
Nov 28 Adversarial examples   7.13  
Nov 30 Negative results      
Dec 1 Final project Q/A      
Dec 5 Final project flash presentations     Final project due 11:59pm
Dec 7 Final project competition      
Dec 8 Nagging TA for better grade      

Prerequisites

Class overview

Goals of the class

After this class you should be able to

Grading

There will be a homework assignment every week, but we will keep them small and manageable. Most of the homework will be graded automatically, you’ll have access to a partial grader while you’re working on the assignment. We will use the same grader, but different test data for your final grade. You’ll submit your homework through canvas.

Late policy:

Expected workload

Estimates of required effort to pass the class are:

Course material

The course should be self contained, but if you need additional reading material consult Deep learning, Goodfellow, Bengio and Courville 2016 www.deeplearningbook.org.

Notes

Syllabus subject to change.