User Tools

Site Tools


schedule-sandbox

Table of Contents

Schedule

January

Week Topic Material Reading Assignments
Week 1:
Jan 21, 23
Overview of course, kinds of machine learning, python, jupyter notebooks, and mathematics of machine learning. 01 Course Overview
01 High-D Spaces
02 Matrices and Plotting
From Python to Numpy, Chapters 1 - 2
Scipy Lectures, Section 1
Deep Learning, Chapters 1 - 5.1.4
Week 2:
Jan 28, 30
Fitting linear models to data as a direct matrix calculation, and incrementally using stochastic gradient descent (SGD) 03 Linear Regression Deep Learning, Section 5.1.4 and 5.9

February

Week Topic Material Reading Assignments
Week 3:
Feb 4, 6
Stochastic gradient descent (SGD). Ridge regression. Data partitioning. Probabilistic Linear Regression. Regression with fixed nonlinearities. 04 Linear Regression Using Stochastic Gradient Descent (SGD)
05 Linear Ridge Regression and Data Partitioning
07 Linear Regression with Fixed Nonlinear Features
Deep Learning, Section 7.3
The Great A.I. Awakening, by Gideon Lewis-Krause, NYT, Dec 14, 2016.
Week 4:
Feb 11, 13
Introduction to nonlinear regression with neural networks. 08 Stochastic Gradient Descent with Parameterized Activation Function Deep Learning, Chapter 6 (skip 6.2) A1 Stochastic Gradient Descent for Simple Models due Tuesday, February 12, 10:00 PM.
Examples of good solutions
Week 5:
Feb 18, 20
More neural networks 09 Scaled Conjugate Gradient for Training Neural Networks
10 More Nonlinear Regression with Neural Networks
Week 6:
Feb 25, 27
Autoencoders. Activation functions. 11 Autoencoder Neural Networks Searching for Activation Functions, by Ramachandran, Zoph, and Le
Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks, by Eger, Youssef, and Gurevych
A2 Adam vs SGD due Tuesday February 26, 10:00 PM.

March

Week Topic Material Reading Assignments
Week 7:
Mar 3, 5
Classification. LDA and QDA. K-Nearest Neighbors. 12 Introduction to Classification
13 Gaussian Distributions
Jupyter Lab: Evolution of the Jupyter Notebook by Parul Pandey
Week 8:
Mar 10, 12
Classification with Neural Networks 14 Classification with Linear Logistic Regression
15 Classification with Nonlinear Logistic Regression Using Neural Networks
A3 Neural Network Regression and Activation Functions due Friday March 15, 10:00 PM.
Mar 16 - 20 Spring Break
Week 9:
Mar 24, 26
Pytorch. 16 Introduction to Pytorch

April

Week Topic Material Reading Assignments
Week 10:
Mar 31, Apr 2
Pytorch. Convolutional Neural Networks 17 Pytorch autograd, nn.Module
18 Convolutional Neural Networks
19 Convolutional Neural Networks in Pytorch
Pytorch Automatic Differentiation
PyTorch Autograd Explained - In-depth Tutorial, by Elliott Waite
Week 11:
Apr 7, 9
Reinforcement Learning. Games using Tabular Q functions. 22 Introduction to Reinforcement Learning
23 Reinforcement Learning with Neural Network as Q Function
Reinforcement Learning: An Introduction, by Sutton and Barto, 2nd ed. Project proposal due at 10 pm Friday evening.
Week 12:
Apr 14, 16
Reinforcement Learning using Neural Networks as Q functions. 24 Reinforcement Learning to Control a Marble
25 Reinforcement Learning for Two Player Games
A4 Classifying Hand-Drawn Digits due Wednesday, April 17
Week 13:
Apr 21, 23
Unsupervised Learning. Dimensionality Reduction. Clustering. 26 Genetic Algorithm Search
27 Linear Dimensionality Reduction
28 K-Means Clustering
Week 14:
Apr 28, 30
Hierarchical clustering. K Nearest Neighbors Classification. Support Vector Machines. 29 Hierarchical Clustering
30 Nonparametric Classification with K Nearest Neighbors
31 Support Vector Machines

May

Week Topic Material Reading Assignments
Week 15:
May 5 - May 7
Ensembles. Other topics. 32 Ensembles of Convolutional Neural Networks
33 Machine Learning for Brain-Computer Interfaces
34 Modeling Global Climate Change
May 11 - 15 Final Exams Final Project Report due Tuesday, May 14, 10:00 PM. Here are is a links to most of the project reports
schedule-sandbox.txt · Last modified: 2020/01/14 15:33 (external edit)