\(~\)

Welcome to the website for Sta-395, Introduction to Machine Learning! To begin, you can find the course syllabus linked below:

You can locate course content by scrolling, or by using the navigation bar in the upper-left.

Course Materials

Most class meetings involve both lecture and lab components. Topics are organized into units, which can be found below. The assignments and due-dates for a given week can be found below that week’s course materials. Unless otherwise indicated, all assignments are to be submitted via Canvas by 11:59pm.

\(~\)

Unit #1 - Concepts, Workflow, and Methods for Tabular Data

Week 0/1 - Introduction to Python and sklearn

Date Lecture Lab Resources
Th 8/28 Introduction Lab 1 - Crash Course in Python
T 9/2 KNN and Decision Trees Finish Lab 1
Th 9/4 Data Pre-processing Lab 2 - Introduction to sklearn
  • Lab 1 is due Monday 9/8 at 11:59pm on Canvas
  • Lab 2 is due Wednesday 9/10 at 11:59pm on Canvas

\(~\)

Week 2 - Cross-validation and model comparisons

Date Lecture Lab Resources
T 9/9 Finish/discuss Lab 2
Th 9/11 Cross-validation Lab 3 - Pipelines and Cross-Validation
  • Homework 1 is due Friday 9/12 at 11:59pm on Canvas
  • Lab 3 is due Wednesday 9/17 at 11:59pm on Canvas

\(~\)

Week 3 - Classifier performance

Date Lecture Lab Resources
T 9/16 Assessing classifier performance Finish/discuss Lab 3
Th 9/18 Lab 4 - Scoring Metrics
  • Homework 2 is due Monday 9/29 at 11:59pm on Canvas
  • Lab 4 is due Wednesday 9/24 at 11:59pm

\(~\)

Week 4 - Regression and machine learning

Date Lecture Lab Resources
T 9/23 Feature Transformations and Expansions Finish/discuss Lab 4
Th 9/25 Regression for Classification Lab 5 - Regression and Machine Learning
  • Lab 5 is due Wednesday 10/1 at 11:59pm

\(~\)

Week 5 - Regularization

Date Lecture Lab Resources
T 9/30 Regularization Finish/discuss Lab 5
Th 10/2 Lab 6 - Regularized Regression
  • Lab 6 is due Wednesday 10/8 at 11:59pm
  • Homework 3 is due Friday 10/17 at 11:59pm
    • Benchmark scores for this assignment will be released soon \(~\)

Week 6 - More Models

Date Lecture Lab Resources
T 10/7 Support Vector Machines Lab 7 - Support Vector Machines An Idiot’s Guide to SVMs
Th 10/9 Random Forest Lab 8 - Ensembles and Feature Engineering
  • Lab 7 is due Monday 10/14
  • Lab 8 is due Wednesday 10/16

\(~\)

Week 7 - More Models (cont.)

Date Lecture Lab Resources
T 10/14 Gradient Boosting Lab 8 (cont.)
Th 10/16 Lab 9 - Gradient Boosting with xgboost
  • Lab 9 is due Friday 10/17

\(~\)

Unit #2 - Mathematics and “Deep Learning”

Week 8 - Gradient Descent Algorithms

Date Lecture Lab Resources
T 10/28 Lab 10 - Linear Algebra Review
Th 10/30 Gradient Descent Algorithms
  • Lab 9 (from before break) is due Wednesday 10/29
  • Lab 10 is due Friday 10/31
  • Homework 4 is due Tuesday 11/11

\(~\)

Week 9 - Neural Networks and Backpropogation

Date Lecture Lab Resources
T 11/4 Lab 11 - Gradient Descent Algorithms
Th 11/6 Neural Networks Finish/discuss Lab 11
  • Lab 11 is due Friday 11/7

\(~\)

Week 10 - Convolutional Neural Networks

Date Lecture Lab Resources
T 11/11 Convolutional Neural Networks Lab 13 - Convolutional Neural Networks
Th 11/13 Lab 14 - Transfer Learning

\(~\)

Week 11 - Exam Preparation

Date Lecture Lab Resources
T 11/18 Exam Review Finishing up previous labs
Th 11/20 Exam
  • Our exam is on Thursday 11/20. We will have a review session on Tuesday 11/18 and you will be able to retake up to 3 quizzes at the end of the review session.
  • Here is a practice exam. It is slightly shorter than the actual exam will be, but it should provide a good indication of the format and style of questions used in the actual exam.

\(~\)

Week 12 - Recurrent Neural Networks

Date Lecture Lab Resources
T 11/25 Reccurent Neural Networks Lab 15
Th 11/27 No class - Thanksgiving

\(~\)

Week 13

Date Lecture Lab Resources
T 12/2
Th 12/4

\(~\)

Week 14

Date Lecture Lab Resources
T 12/9 Project Presentations #1
Th 12/11 Project Presentations #2

\(~\)

Final Project

Final Project Description

  • The first project deadline is Tuesday 10/28 - one team member must indicate all members of your project team via email
  • The second project deadline is Friday 10/31 - one team member must share a short (1-2 paragraph) proposal via email describing your planned topic, including the data source.