Schedule

Contents

Schedule#

Warning

As this is a new course, the schedule may change throughout the semester to best accommodate your learning!

Topics#

A list of topics we will cover can be found below. Note that topics may be subject to change.

  • Regression

  • Gradient descent

  • Classification

  • Model selection and evaluation

  • Regularization

  • Feature engineering

  • Fairness and interpretability

  • Ensembling

  • Neural networks

  • Unsupervised learning

    • K-means clustering

    • Autoencoders

Monday

Tuesday

Wednesday

Thursday

Friday

1/26

1/27
Introduction

Survey 1

1/28

1/29
kNN, Math, NumPy

Worksheet 1

1/30

2/2
Survey 1

2/3
Linear Regression

2/4
Worksheet 1

2/5
Gradient Descent I

Homework 1

2/6

Homework 1

2/9

2/10
Gradient Descent II

2/11

2/12
Model evaluation

2/13
Homework 1

2/16
Homework 1

2/17
Regularization

Worksheet 2

2/18

2/19
Classification I

2/20

2/23
Worksheet 2

2/24
Classification II

Homework 2

2/25

2/26
Classification Metrics

2/27

3/2

3/3
ROC Curves

3/4
Homework 2

3/5
Fairness

Survey 2

3/6
Worksheet 3

3/9

3/10
Trees and Ensembling I

3/11
Worksheet 3

3/12
Ensembling II

Final project proposal

3/13
Worksheet 3
Survey 2

03/16 - 3/22
🌼 Spring break 🌸

3/23

3/24
Bootstrapping and Variance


HW 3

3/25

3/26
Neural Networks I

3/27

3/30
Final project proposal

3/31
Neural Networks II

4/1

4/2
Neural Networks III

4/3
HW 3
HW 4

4/6

4/7
Unsupervised Learning I

4/8

4/9
Unsupervised Learning II

4/10

4/13
HW 4
Tony away this week, but available via Ed/email

4/14
Guest lecture: Word embeddings

Worksheet 4
Course survey 3

4/15

4/16
[video] ML engineering

4/17

4/20
Worksheet 4
Course survey 3

4/21
Project check-ins

4/22

4/23
Special topic: Language Models

4/24

4/27
Final project checkpoint

4/28
BOOM - no class

4/29

4/30
Presentations I

5/1

5/4

5/5
Presentations II and wrap-up

5/6

5/7

5/8

5/11

Final project (noon)

5/12

5/13

5/14

5/15