CS 342 - Neural networks - Fall 2018

meets
TTh 10am-11am UTC 3.124
Fr 1pm-2pm / 2pm-3pm ECJ 1.204

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 TBD
TA hours TBD

We will use piazza for questions and canvas homework.

Schedule

class section

Date	Topic	Concepts	Slides	Corresponding book chapters (optional; see below)	Notes and due dates
Aug 30	Introduction	tensors layers		Background: Ch 1-5
Aug 31	Installing pytorch and building the first compute graph				HW1 out
Sep 4	Simple networks	fully connected ReLU
Sep 6	Output transformations and loss functions	sigmoid softmax log likelihood L1/L2 loss		5.9	HW1 due 11:59pm
Sep 7	Logistic regression and MLP				HW2 out
Sep 11	Back propagation	back prop		Ch 6
Sep 13	Stochastic gradient descent	SGD momentum			HW2 due 11:59pm
Sep 14	Regression vs classification				HW3 out
Sep 18	Activation functions + Initialization	LeakyReLU PReLU Gaussian Init Xavier Init		Ch 6
Sep 20	Convolutions + Pooling	Conv2D Avg Pooling Max Pooling striding / padding		9.1-9.3	HW3 due 11:59pm
Sep 21	ConvNets				HW4 out
Sep 25	Overfitting	early stopping data augmentation dropout parameter sharing ensembles		7.4, 7.8, 7.9, 7.11, 7.12
Sep 27	Optimization tips and tricks	weight regularization batch normalization		7.1-7.3	HW4 due 11:59pm
Sep 28	Regularization and normalization				HW5 out
Oct 2	Popular Architectures I	LeNet AlexNet VGG auxillary losses
Oct 4	Popular Architectures II	GoogLeNet ResNet DenseNet residual connections			HW5 due 11:59pm
Oct 5	ResNets				HW6 out
Oct 9	Object detection	ROI Pooling R-CNN Fast R-CNN YOLO
Oct 11	Segmentation	up-convolution FCN			HW6 due 11:59pm
Oct 12	Fully convolutional networks				HW7 out
Oct 16	Visualization and understanding	gradients and saliency
Oct 18	Generative models	reparametrization trick adversarial loss		20.10, 20.12, 20.13	HW7 due 11:59pm
Oct 19	Upconvolution and deep rendering				HW8 out
Oct 23	Recurrent Network I	RNN LSTM GRU		10.1-10.11
Oct 25	Recurrent Network II	Temporal CNNs			HW8 due 11:59pm
Oct 26	Future prediction				HW9 out
Oct 30	Deep Reinforcement Learning I	policy gradient
Nov 1	Deep Reinforcement Learning II	Q-learning actor-critic			HW9 due 11:59pm
Nov 2	Acting through future prediction				HW10 out
Nov 6	Deep Reinforcement Learning III	gradient free optimization
Nov 8	Acting with supervised learning	imitation learning dagger direct future prediction			HW10 due 11:59pm
Nov 9	Gradient free optimization				HW11 out
Nov 13	Embedding learning	triplet loss contrastive loss
Nov 15	Style transfer	graham statistic			HW11 due 11:59pm
Nov 16	Driving in SuperTuxKart				Final project out
Nov 20	Language
Nov 22	no class
Nov 23	no class
Nov 27	Adversarial examples		adversarial attack	7.13
Nov 29	Negative results
Nov 30	Final project Q/A
Dec 4	Final project flash presentations				Final project due 11:59pm
Dec 6	Final project competition
Dec 7	Nagging TA for better grade				no class

concepts: layers/architecture algorithm supervision applications

Prerequisites

• 311 or 311H - Discrete math for computer science (or equivalent)
• 343 or 363D - Artificial Intelligence or Statistical Learning and Data Mining
• proficiency in Python
  • Bonus: numpy, scipy and matplotlib

Class overview

• The class meets three times a week, twice is a classroom setting, once in a lab setting
• In the classroom setting you’ll learn the theoretical and mathematical background on neural networks and deep learning
• In the lab you’ll learn to use tensorflow and implement the techniques learned in class

Goals of the class

After this class you should be able to

• Implement and train neural networks in tensorflow
• Have a basic understanding of the inner workings of neural networks
• Know several types of neural networks, including convolutional and recurrent neural networks

Grading

• 10% Quizzes (in class)
• 55% Homework
• 35% Final project

There will be in class quizzes throughout the semester (about one a week). You can work with your peers on those quizzes during class. Each quiz will be graded pass/fail.

There will be a homework assignment every week, but we will keep them small and manageable. Homework needs to be solved individually, if we detect duplicate solutions you will lose the full credit for the assignment. 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:

• 1 day: -25%
• 2 days: -50%
• 3+ days: -100%

Expected workload

Estimates of required effort to pass the class are:

• 3 hours per week: attend class
• 3 hours per week: background reading
• 3 hours per week: coding homework

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.