Machine Learning Spring 2026

Education Research

Day #	Activity
1	Course intro and welcome to ML!
2	ML as Optimization and Linear Regression
3	Human-Centered Design for Machine Learning
4	Visit from Brian Charlson and Design Sprint
5	Linear, Ridge, and Logistic Regression & Train-Test Split
6	Logistic Regression Sample Problem, Foundations of Micrograd
7	Building Towards Autodifferentiation
8	From Micrograd to Pytorch and Starting COMPAS
9	Validation sets, project planning, and multilayer perceptron
10	COMPAS discussion
11	Overfitting in Neural Networks and Project Work Time
12	Project Shareout and Starting Text as Data
13	Introduction to Transformers
14	Self-Attention in Transformers
15	Choose Your Own Adventure
16	Trust and Trustworthiness in Machine Learning and Starting BERT
17	SBERT and Finetuning
18	Goodbye Text, Hello Images and Convolution
19	Convolutional Neural Networks and Privacy in ML
20	GANs, Diffusion, and Final Project Launch
21	Review Project Proposals
22	Project Worktime
23	Energy Usage of LLMs and Project Worktime

Due at beginning of class #	Assignment
2	Assignment 1 (with show solution button)
3	Assignment 2 (with show solution button)
4	Assignment 3
5	Assignment 4
6	Assignment 5 (with show solution button)
6	Assignment 6 (with show solution button)
8	Assignment 7 (with show solution button)
9	Assignment 8
10	Assignment 9 (with show solution button)
12	Small data mini-project on classification
13	Bag of Words, Text Classification, and Word Embeddings (with show solution button)
14	Generative Pre-Trained Transformers (GPTs) Part 1
15	Trust and Trustworthiness of Machine Learning Models
16	Generative Pre-Trained Transformers (GPTs) Part 2 (with show solution button)
17	Transformers for Text Embedding (with show solution button)
18	SBERT and Finetuning
19	Images as Data and Convolutions (with show solution button)
20	Convolutional Neural Networks (ConvNets, CNNs) in Code
final event	Final Project