CS 7180: Special Topics in AI

Imaging and Deep Learning - Experiments, Derivations, and Theory

Time & Location:

6:00 - 9:15pm, T, Location: Hurtig Hall 224

Staff

Instructor: Paul Hand
    Office: TBD

Overview

In each day of class, the first half will consist of a lecture given by the instructor. In the second half, there will be a presentation and discussion on two papers related to the previous class’s lecture. A student (or a pair of students) will lead the presentation/discussion on each of the papers. To prepare for each day of class you should:

• Review your notes from the lecture portion of the previous class
• Read the two papers that are assigned for that day's class. For each paper, come to class with a sheet of paper that has: your name, at least one question related to the paper that you would like to have a class discussion about. Bring a separate sheet of paper for each paper.

To prepare a class presentation/discussion:

• Provide a clear context for the paper. (eg. What problem or task is being solved? Why is it being solved? )
• Convey some scientific content.
• Provide explanation/justification/demonstration as relevant.
• Discuss potential consequences of the work.
• Have some question or task which you will ask the audience to answer or do for a couple minutes. (eg. You could show a figure with the legend removed and ask the audience what the legend is)
• Remember: you should think of your presentation as being about the ideas of the paper, and less as being about the paper itself
• Remember: be ruthless about excluding ideas that are not your central point.
• You should spend about 20 minutes presenting the paper, 5 minutes for a task for the audience, and 20 minutes for a discussion

Each day of class, about half will consist of lecture and half of presentations and discussions on individual papers.

Students will present at most two papers during the semester and will do one project. The project will involve implementing the methods in a paper related the class content. The project will involve replicating some of the results of the paper in addition to presenting additional observations that were not remarked upon in the paper. You will give a 5 minute presentation during the last two weeks of class and you will write an at-most 4 page paper detailing your findings. Please use the NeurIPS Style Files. Your writeup should contain a description of the scientific context of your project, should clearly state a question or hypothesis that is being (partially or completely) answered, detail what you did, state what you observed, and then discuss the implications and subsequent work that is motivated by your results. It is fine if your project is a negative result. Your project should include references, which are not counted in the 4 page limit. The paper is due on the last day of class.

The class will assume you are fluent in linear algebra and probability. It will assume you have some experience with neural networks, python, Pytorch/Tensorflow/etc. Students taking the class for a grade are expected to participate in the discussions in almost all classes, in addition to presenting their two papers and project.

Prerequisites

The class will assume students are fluent in linear algebra and probability. Some experience with neural networks, python, PyTorch/TensorFlow will be helpful.

#	Date	First Half	Second Half
1	T 1/7	Course Overview	Signal Recovery and Compressed Sensing
2	T 1/14	Discrete Fourier Transforms, Wavelet Transforms, Algorithms for Sparse Recovery	Improved Pediatric MR Imaging with Compressed Sensing Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
3	T 1/21	ML Framework: Bias-Variance Tradeoff Linear Regression Logistic Regression KL Divergence Cross Entropy	Recovering low-rank matrices from few coefficients in any basis Robust Principal Component Analysis?
4	T 1/28	Optimization Methods: GD,SGD,Adam,LBFGS	Reconciling modern machine learning and the bias-variance trade-off Deep Double Descent: Where Bigger Models and More Data Hurt
5	T 2/4	Work on Projects	---
6	T 2/11	Architectural Elements: Convolutions Transpose Convolutions Activation Functions Batch Normalization Upsampling/Downsampling	Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming (see also Zeroth Order Optimization with Applications to Adversarial Machine Learning slides online) Accelerating Stochastic Gradient Descent using Predictive Variance Reduction
7	T 2/18	End-to-end Approaches	Deconvolution and Checkerboard Artifacts How Does Batch Normalization Help Optimization?
8	T 2/25	Variational Autoencoders	Image Super-Resolution Using Deep Convolutional Networks A Deep Learning Approach to Structured Signal Recovery
	T 3/3	No Class. Spring Break	---
9	T 3/10	GANs: Derivation, Variations	The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
10	T 3/17	GANs: Recovery Theory Notes Video	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Progressive Growing of GANs for Improved Quality, Stability, and Variation
11	T 3/24	Untrained Nets: Deep Image Prior, Deep Decoder, Deep Geometric Prior Notes Video	Phase Retrieval Under a Generative Prior The spiked matrix model with generative priors
12	T 3/31	Invertible Nets Notes Video	"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
13	T 4/7	Projects	Projects
14	T 4/14	Projects	Projects