Sidebar
schedule
This is an old revision of the document!
Schedule
Announcements
May 9: At the bottom of this page is a link to a summary of the content expected in your project reports.
April 29: My latest neural network code is available at nn7.tar.
January
| Week | Topic | Material | Reading | Assignments |
|---|---|---|---|---|
| Week 1: Jan 19 - Jan 22 | Overview. Intro to machine learning. Python. | 01 Course Overview, 02 Matrices and Plotting, | Text: Sections 1.1-1.5. Section 1 of Scipy Lecture Notes | |
| Week 2: Jan 25 - Jan 29 | Probability distributions and regression. | 03 Linear Regression, 04 Gaussian Distributions, 05 Fitting Gaussians, 06 Probabilistic Linear Regression | Sections 4.1-4.2, 4.6-4.9, 5.8-5.9 | A1 Linear Regression due Friday, January 29th at 10:00 PM. Download and unzip A1 Grader.zip Here are five examples of good solutions: A1a, A1b, A1c, A1d, A1e |
February
| Week | Topic | Material | Reading | Assignments |
|---|---|---|---|---|
| Week 3: Feb 1 - Feb 5 | Ridge regression. Data partitioning. On-line, incremental regression. Regression with fixed nonlinearities. | 07 Linear Ridge Regression and Data Partitioning, 08 Sample-by-Sample Linear Regression, 09 Linear Regression with Fixed Nonlinear Features | ||
| Week 4: Feb 8 - Feb 12 | Nonlinear regression with neural networks. | 10 Nonlinear Regression with Neural Networks, 11 More Nonlinear Regression with Neural Networks | 11.1-11.5, 11.7.1, 11.7.4, 11.8.1-11.8.2 | |
| Week 5: Feb 15 - Feb 19 | Autoencoders. Recurrent neural networks. | 12 Autoencoder Neural Networks 13 Recurrent Neural Networks | 11.9, 11.12, 11.14 | A2 Linear Regression with Fixed Nonlinear Features due Monday, Feb 15 at 10:00 PM. Here are three examples of good solutions: A2a, A2b, A2c |
| Week 6: Feb 22 - Feb 26 | Classification, generative models. | 14 Introduction to Classification | 4.3-4.5, 5.5-5.7 |
March
| Week | Topic | Material | Reading | Assignments |
|---|---|---|---|---|
| Week 7: Feb 29 - Mar 5 | Classification, Introduction to Support Vector Machines. | Monday: GTA Jake Lee will discuss questions on Assignment 3. Wednesday: Guest lecture by Dr. Asa Ben-Hur. 15 Classification with Linear Logistic Regression SVM Slides | 10.1-10.4, 10.5-10.10 | A3 Neural Network Regression due Monday, Feb 29 at 10:00 PM. Here are examples of good solutions: A3a, A3b, A3c,A3d, A3e, A3f,A3g, A3h |
| Week 8: Mar 7 - Mar 11 | Classification with neural networks. | 16 Classification with Nonlinear Logistic Regression Using Neural Networks | 11.7.2 | |
| Mar 14 - Mar 18 | Spring Break! | |||
| Week 9: Mar 21 - Mar 25 | Bottleneck, and deep networks. | 17 Analysis of Neural Network Classifiers and Bottleneck Networks 18 Digits | 11.8.3, 11.11, 11.13 | |
| Week 10: Mar 28 - Apr 1 | Convolutional neural nets. Clustering. | 19 Convolutional Neural Networks 20 Clustering 21 Mixtures of Gaussians | 7.1-7.10 | A4 Classification with LDA, QDA, and Logistic Regression due Tuesday, March 29 at 10:00 PM. Here are examples of good solutions: a4a, a4b, a4c,a4d, a4e, a4f,a4g, a4h |
April
| Week | Topic | Material | Reading | Assignments |
|---|---|---|---|---|
| Week 11: Apr 4 - Apr 8 | Reinforcement Learning | 22 Introduction to Reinforcement Learning 23 Reinforcement Learning for Two Player Games 24 Reinforcement Learning with Neural Network as Q Function | 18.1-18.9 | |
| Week 12: Apr 11 - Apr 15 | Dimensionality reduction. | 25 Tic-Tac-Toe with Neural Network Q Function 26 Linear Dimensionality Reduction 27 Nonlinear Dimensionality Reduction with Digits Example | 6.1-6.8, 6.10-6.13 | |
| Week 13: Apr 18 - Apr 22 | Nonparametric methods | 28 Nonparametric Classification with K Nearest Neighbors, 29 Support Vector Machines | 8.1-8.10 | A5 Reinforcement Learning Solution to Visual Tic-Tac-Toe due Wednesday, April 20 at 10:00 PM. Here are examples of good solutions: a5a, a5b, a5c,a5d, a5e, a5f,a5g Check in your Project Proposal by Friday, April 22nd, at 10:00 PM |
| Week 14: Apr 25 - Apr 29 | 31 Machine Learning for Brain-Computer Interfaces, 32 Comparison of Algorithms for BCI, 33 Convolutional Neural Networks for BCI |
May
| Week | Topic | Material | Reading | Assignments |
|---|---|---|---|---|
| Week 15: May 2 - May 6 | Multiple models. PLEASE ATTEND MAY 6th LECTURE TO FILL OUT THE ASCSU STUDENT COURSE SURVEYS! Distance-section students will be filling out the survey on-line. | 34 Ensembles of Convolutional Neural Networks, 35 Ensembles of Convolutional Neural Networks for BCI | 17.1-17.12 |
| Week 16: May 10 | Final Project Notebook Due. | Check in final project notebook by Tuesday, May 10th, at 10:00 PM. Here is a summary of what is expected in your reportsl |
Selected Project Reports (in no particular order):
schedule.1481726806.txt.gz · Last modified: 2016/12/14 07:46 by anderson
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 4.0 International
