User Tools

Site Tools


schedule

Table of Contents

Schedule Spring 2020

Examples of good solutions are now available at this site.

January

Week Topic Material Reading Assignments
Week 1:
Jan 21, 23
Overview of course, kinds of machine learning, python, jupyter notebooks. 01 Course Overview
01a Matrix Multplication on GPU
02 Matrices and Plotting
03 Linear Regression with SGD
Week 2:
Jan 28, 30
Supervised learning. Linear and nonlinear regression with artificial neural networks. 04 Linear Regression with Fixed Nonlinear Features
05 Introduction to Neural Networks

February

Week Topic Material Reading Assignments
Week 3:
Feb 4, 6
Gradient descent with Adam. Effects of network size and other parameters. 05 Introduction to Neural Networks
06.1 Gradient Descent with Adam
A1.1 Linear Regression with SGD due Thursday, Feb 6th, at 10:00 PM
Week 4:
Feb 11, 13
Optimizers class. NeuralNetwork class. Partioning data. 07.2 Optimizers, Data Partitioning, Finding Good Parameters HiPlot a new plotting library for visualizing results from multiple training experiments Exercises1. Do not check-in. Exercises will not be graded.
Week 5:
Feb 18, 20
Pytorch basics, loss functions, optimizers and nn module. 08 Pytorch autograd, nn.Module LaProp optimizer A2.5 Multilayer Neural Networks for Nonlinear Regression due Thursday, Feb 20th 10:00 PM
Week 6:
Feb 25, 27
Classification with generative models. LDA and QDA. 09 Introduction to Classification

March

Week Topic Material Reading Assignments
Week 7:
Mar 3, 5
Classification with linear logistic regression 10 Classification with Linear Logistic Regression The unreasonable effectiveness of deep learning in artificial intelligence A3.3 Cross-validation with Pytorch due Thursday, March 5th, 10:00PM
Week 8:
Mar 10, 12
Class inheritance. Nonlinear logistic regression with neural nets. 11 Code Reuse by Class Inheritance
12.1 Classification with Nonlinear Logistic Regression Using Neural Networks
Mar 16 - 20 Spring Break
Week 9:
Mar 24, 26
Start of online-only lectures. Thursday this week is first online class. No new material covered, but assignment questions can be discussed. Join the Microsoft Teams meeting using your firstname.lastname@colostate.edu login.

April

Week Topic Material Reading Assignments
Week 10:
Mar 31, Apr 2
Convolutional neural networks 13 Convolutional Neural Networks, 14 Convolutional Neural Network Training with Numpy
Week 11:
Apr 7, 9
Classification with Pytorch. Assignment 5. , with discrete state and action using tables and neural networks. 15 Convolutional Neural Networks in Pytorch A4.2 Classification of Hand-Drawn Digits due Tuesday, April 7th, 10:00PM
Week 12:
Apr 14, 16
Reinforcement learning. 16 Introduction to Reinforcement Learning
17 Reinforcement Learning with Neural Network as Q Function
Reinforcement Learning: An Introduction, by Richard Sutton and Andrew Barto, 2nd edition Project Proposal due Thursday, April 16th, 10:00PM
A5.4 2-D and 1-D Convolutional Neural Networks in Pytorch due Saturday, April 18th, 10:00PM
Week 13:
Apr 21, 23
Reinforcement learning. History and future of AI as discussed in episode of AI Element Podcast 18.1 Reinforcement Learning to Control a Marble
19 Reinforcement Learning for Two Player Games
Week 14:
Apr 28, 30
Linear and Nonlinear Dimensionality Reduction 20 Linear Dimensionality Reduction
21.1 Nonlinear Dimensionality Reduction with Autoencoder Neural Networks
A6.2 Tic Tac Toe due Friday May 1st by 10:00 PM.

May

Week Topic Material Reading Assignments
Week 15:
May 5, 7
Unsupervised learning. Clustering, K-Means 22 K-Means Clustering Find data on COVID-19 cases updated daily and display using matplotlib A7.1 Autoencoder for Classification due Friday May 8th by 10:00 PM.
May 11 - 15 Final Exam Week Project Report due Tuesday, May 12, 10:00 PM.
schedule.txt · Last modified: 2020/05/08 11:30 by anderson