ECE228 Machine learning for physical applications, Spring 2020
Final Projects 2020
Final Projects 2019 and Spring 2019 class
Class is currently on Canvas, it is not updated
Professor Peter Gerstoft, Spiess Hall 462, Gerstoft@ucsd.edu
TA Ruixian Liu, rul188@eng.ucsd.edu
TA Venkatesh Sathyanarayanan,
TA Brian Whiteaker,
TA Emma Reeves,
TA Raghav Subramanian,
Location: Peterson Hall 110
Time: Monday and Wednesday 56:20pm
Sylabus: Machine learning has received enormous interest. To learn from data we use probability theory, which has been the mainstay of statistics and engineering for centuries. The class will focus on implementations for physical problems. Topics: Gaussian probabilities, linear models for regression, linear models for classification, neural networks, kernel methods, support vector machines, graphical models, mixture models, sampling methods, sequential estimation. Prerequisites: graduate standing.
It is not a computer science class, so we go slowly through the fundamentals to appreciate the methods, implement these. We will discuss their use in Physical Sciences. In the first part of the class we focus on theory and implementations. We will then transition to focus on machine learning final projects.
Books (available online): Main book:
Goodfellow, Ian, Yoshua Bengio, and Aaron Courville, Deep Learning
https://www.deeplearningbook.org/
We will start from chapter 6
Other good books:
In the past, I have used the Bishop book, some residue will remain
Chris M Bishop
Pattern
Recognition and Machine Learning . A third party Matlab implementation of many of the
algorithms in the book.
Hastie and Tibshirani
The Elements of Statistical Learning
Kevin P. Murphy: Machine Learning: A Probabilistic Perspective.
UCSD license
. Matlab codes used in Murphy's
book.
Online resources: While not required, I recommend taking these classes. Both
are online classes are excellent.
Statistical
Learning by Hastie and Tibshirani. My favorite class.
Andrew Ng's Coursera class, Machine learning. This was the first class offered
by Coursera.
Grading: Full scale of the letter grade. Grade consists of About
50 % homework and 50% finalproject (10% poster, 10 % code and 30 % Report). Your and my purpose
is to lean, so a good effort is sufficient.
Homework Homework will be graded. I'm a strong believer in leaning by doing. Thus we will
have computerbased homework each week.
Final project: Propose a topic before May 1.
We will make teams on ~April 26.
Suggested topics (see last years projects
Spring 2019 ,
Spring 2018, and Spring 2017
):
Schedule (15 Lectures. poster session and discussion )
Lecture  Date  Topic  Required reading  Assignments 
1  March 30  Introduction, probability theory [Slides Annotated Slides ] 
Bishop CH 1.01.2  
2  April 2  Question to lecture 2 in Stanford CNN lecture  Bishop CH 1.5, 1.6, 2.3  
3  April 6  Bishop CH 2.3, 6.4 Murphy ch15 
Homework 1 due 4/22  
4  April 8 
[Slides Annotated Slides] Question to lecture 5 in Stanford CNN lecture  Bishop CH 3.03.1  Homework 2 due 4/22 
5  April 13  [Slides Annotated Slides] Question to lecture 6 in Stanford CNN lecture 
Bishop CH 3.23.3  
6  April 15 
Question to lecture 7 in Stanford CNN lecture [Slides Annotated Slides] 
GPU Jupiter homework relased due 5/10  
7  April 20  Question to lecture 8 in Stanford CNN lecture [Slides Annotated Slides] 
Bishop 4.04.3.2, 4.3.4, 5.05.2  Homework 3 (NN) due 5/5. Subset of MNIST Data to use for HW3 on you laptop 
8  April 22  Question to lecture 9 in Stanford CNN lecture [Slides Annotated Slides] 
Bishop CH  
9  April 27 
Question to lecture 10 in Stanford CNN lecture Christopher Johnson: Machine learning with CNN in seismology. [Slides Annotated Slides] 
Bishop CH 6  
10  April 29 
Question to lecture 11 in Stanford CNN lecture [Slides Annotated Slides] 
Bishop CH 7  
May 4  No Class start on Project [Slides Annotated Slides]  Bishop CH 9  Homework 5(SVM +Dictionary Learning) due 5/29  
May 6  No Class, work on Final project. Mike Bianco: Dictionary leaning  Read Bianco's Dictionary learning paper  
11  May 11 
Question to lecture 12 in Stanford CNN lecture Question to lecture 13 in Stanford CNN lecture  
12  May 13  
13  May 18 
Question to lecture 13 and 14 in Stanford CNN lecture [Slides Annotated Slides] 
Bishop CH 13  
14  May 22  
May 27  Project poster presentation, Qualcomm Auditorium and Jacobs Lobby, 58 pm  Poster Review due June 30  
15  June 1 
Question to lecture 15 in Stanford CNN lecture [Slides Annotated Slides]  Homework 6 (Kalman Filter and Sparse signal recovery) due 6/10


June 3  Final report due Friday 12 June. 