IML — Summer 2023

Sat, 01 Apr 2023 00:00:00 +0000

Lecturer:

Class timing: The is applied here! This means the lecture will start 15 minutes after the said time.

Course Description

Machine Learning has gained a lot of momentum within development organizations that are actively looking for innovative solutions to leverage their data to identify new levels of understanding their operations and processes. Machine learning is a subfield of Artificial Intelligence where the machine learns from data rather than from explicit programming. Machine Learning applications are likely to be part of your daily life without you being aware of it! Take as an example that you might face on a daily basis! This course will walk you through the basics of machine learning and explain how to formulate machine learning problems that are relevant to a wide range of applications. The class will be self-contained; a brief review on probability and information theory will be given before we dive into the main topics; linear and logistic regression, neural networks, non-parametric models, and unsupervised learning.

Course Objectives

Successful students should

gain a basic understanding of machine learning theory
identify the strengths and weaknesses of various machine learning algorithms
be able to formulate machine learning problems that are relevant to a wide range of applications
be able to solve moderately complex problems using machine learning algorithms
be able to apply, adapt and optimize machine learning algorithms to real-world problems
be able to report various performance measures and evaluation metrics

Required Materials

Murphy, K.P., 2022. . MIT press.

Prerequisites

Linear Algebra
Probability Theory
Programming in Python

Course Structure and grading policy (tentative):

Assignments (10%): You will be occasionally given assigments or quizzes which contribute to 10% of your grade
Lab. (20%): You will be given a few lab assignments to have hands-on experience with programming in python
Midterm Exam (20%)
Final Exam/Class Project (50%)

Schedule

Date	Topic	Self-reading
29.09.2022	Introduction (Ch1)
06.10.2022	Foundations: Probability (Ch2)	Statistics (Ch4) + Decicion Theory (Ch5)
13.10.2022	Foundations: Probability (Ch3)	Information Theory (Ch6) + Linear Algebra (Ch7) + Optimization (Ch8)
20.10.2022	Linear Models: Logistic Regression (Ch10)
27.10.2022	Linear Models: Logistic Regression (Ch10) – Cont.	Linear Discriminative Analysis (Ch9)
03.11.2022	Linear Models: Linear Regression (Ch11)	Generalized Linear Models (Ch12)
10.11.2022	Linear Models: Linear Regression (Ch11) – Cont.	Generalized Linear Models (Ch12)
17.11.2022	Mid-term Evaluation
01.12.2022	Neural Networks: NNs for Tabular Data (Ch13)
08.12.2022	Neural Networks: NNs for Tabular Data (Ch13) – Cont. + Lab
15.12.2022	Neural Networks: NNs for Imaging Data (Ch14)
22.12.2022	Beyond Supervised Learning: Dimensionality Reduction (Ch20) + Clustering (Ch21)	Recommender Systems (Ch22)
29.12.2022	Hands-on Experience on the projects
05.01.2023	Course Recap.
19.01.2023	Final Project Evaluation

References

Bishop, C.M. and Nasrabadi, N.M., 2006. (Vol. 4, No. 4, p. 738). New York: springer.
James, G., Witten, D., Hastie, T. and Tibshirani, R., 2013. (Vol. 112, p. 18). New York: springer.

Projects

Interested in the Medical Imaging community!

Listen to our recent talks about Federated Learning in Healthcare ( / )
Join and contribute to the

Contact the organizers

If you have any questions regarding the course, please do not hesitate to contact !

SS23 |