Machine learning for behavioral data

CS-421

Media

CS-421 Machine learning for behavioral data - Spring 2022

MLBD 2023 - Start-ups introduction

21.02.2023, 10:40

Second part of first lecture of the MLBD course 2023 edition.

In this video, the Marco and Anette introduce the start-ups that the students can choose to work on their project. 

13, Explainability

25.05.2022, 12:21

12, Fairness

16.05.2022, 17:14

Structure Discovery 2

09.05.2022, 18:11

Structure Discovery

02.05.2022, 18:03

09, Neuroscience

25.04.2022, 17:13

Guest Speaker - Prof. Mackenzie Mathis

8, Deep Learning

11.04.2022, 17:23

Knowledge Tracing Continued

04.04.2022, 19:05

6, Knowledge Tracing

28.03.2022, 18:40

Model Evaluation

21.03.2022, 18:57

Classification

14.03.2022, 17:28

Regression

07.03.2022, 17:47

Data Exploration

28.02.2022, 17:14

Introduction

21.02.2022, 17:58

12, 05-17-21 Lecture 12 Multimodel Analytics

17.05.2021, 22:30

11, 05-10-21 Lecture 11 Affective Computing

11.05.2021, 11:08

10, 05-03-21 Lecture 10 Advanced Student Modeling

03.05.2021, 18:36

9, 04-26-21 Lecture 09 Advanced Structure Discovery

26.04.2021, 18:21

8, 04-19-21 Lecture 08 Recommender Systems and Structure Discovery Part 2

19.04.2021, 23:33

7, 04-12-21 Lecture 07 Recommender Systems

13.04.2021, 10:31

03-29-21 Lecture 06 Structure Discovery

02.04.2021, 01:08

5, 03-22.21 Lecture 05 Knowledge Tracing

23.03.2021, 16:00

4, 03-15-21 Lecture 04 Model Evaluation

16.03.2021, 17:37

3, 03-08-21 Lecture 03 Regression and Classification

09.03.2021, 14:44

2, 03-01-21 Lecture 02 Data Handling

03.03.2021, 12:46

1, 02-22-21 Lecture 01 Introduction

23.02.2021, 18:37


This file is part of the content downloaded from Machine learning for behavioral data.

Course Information


Introduction

Computer environments such as educational games, interactive simulations, and web services provide large amounts of data, which can be analyzed and serve as a basis for adaptation. This course will cover the core methods of user modeling and personalization, with a focus on educational data.

 

Learning Outcomes

By the end of the course, the student must be able to:

  • Explain the main machine learning approaches to personalization, describe their advantages and disadvantages and explain the differences between them
  • Implement algorithms for these machine learning models
  • Apply them to real-world data
  • Assess / evaluate their performance


Logistics

Lecture / Lab Session:   Tuesday, 13:15-16:00 (INJ 218)

Project Office Hours:    Tuesday, 16:00-17:00 (INJ 218)

Instructor:                      Tanja Käser  (INF 234)

Teaching assistants contact emails: {seyed.neshaei, bahar.radmehr, marta.knezevic} (at) epfl.ch


Schedule

MLBD schedule including project hours and milestones.

Attendance of all individual discussions with teams (feedback sessions), team coachings, as well as the final poster session is MANDATORY!


Course Content 

The lecture slides, demo notebooks, and student notebooks will be uploaded every week to our GitHub repository.

Course GitHub Repository: https://github.com/epfl-ml4ed/mlbd-2025/

Lecture recordings (from 2022)

In-class activity feedback/questions


Grading 

  • 50% Project: teams of 3 people. 15% individual exploration (M2), 25% supervised learning (M4), 20% presentation (M6), 40% final results (M7)
  • 50% Final Exam (Exam Session): individually, at the laptop. Mix of conceptual and coding questions.

Feedback

We are fully committed to providing the best possible version of the course and we appreciate all constructive feedback. 
We are looking forward to reading your comments and improving based on them.

Feedback link (anonymous) 



 

Other Useful Resources


Final Exam 2023

Announcements and Class Questions

Exam Preparation

The exam is composed of two parts:

1) Conceptual questions and 

2) Programming exercises

Exam 2025