Hasso-Plattner-Institut20 Jahre HPI
Hasso-Plattner-Institut20 Jahre HPI
  
Login
 

Machine Learning in Precision Medicine (Sommersemester 2019)

Dozent: Prof. Dr. Christoph Lippert (Digital Health & Machine Learning) , Jana Fehr (Digital Health & Machine Learning) , Dr. rer. nat. Stefan Konigorski (Digital Health & Machine Learning) , M.Sc. Remo Monti (Digital Health & Machine Learning)

Allgemeine Information

  • Semesterwochenstunden: 4
  • ECTS: 6
  • Benotet: Ja
  • Einschreibefrist: 01.04.2019 bis 26.04.2019
  • Lehrform: Vorlesung / Seminar
  • Belegungsart: Wahlpflichtmodul
  • Lehrsprache: Englisch

Studiengänge & Module

Digital Health MA
IT-Systems Engineering MA
Data Engineering MA
  • Datenanalyse

Beschreibung

This course is designed to give students an in-depth introduction to machine learning. The lectures and exercises are designed around biomedical use cases and will use real-world biomedical data to gain practical experience with machine learning models and algorithms. The course will start with an introduction to the basic concepts of machine learning and empirical data analysis, such as model fitting, selection and validation. During the second part of the course, we will discuss supervised machine learning, starting with linear models, to non-linear models, including deep neural networks and convolutional neural networks for medical imaging.  During the third part of the course, we will discuss unsupervised learning, starting with clustering, to dimensionality reduction and latent variable models. While we will discuss machine learning in a biomedical context, the learned principles and algorithms are applicable to other fields as well.

Learning Objectives:

  • Understand concepts, methods and algorithms in machine learning
  • Ability to empirically analyze real-world data
  • Ability to assess the quality and validity of a machine learning model for a given analysis
  • Ability to select, develop, implement and apply appropriate machine learning models and algorithms for a given use case.
  • Gain an introduction to biomedical use cases of machine learning, including clinical prediction problems, medical image analysis, and modeling of multi-omics data.

 

Course Syllabus and Schedule (Summer 2019)

 

Please note that the schedule is still preliminary and details are subject to change.

 

CW / Week

Topic

15 / 1

Introduction

15 / 1

Introduction to Python Part I

16 / 2

Introduction to Python Part II

16 / 2

Linear Regression

17 / 3

Basis Functions, Regularization and Experimental Design

17 / 3

Probabilistic Interpretation and Bayesian Linear regression

18 / 4

Link Functions and Logistic Regression

18 / 4

Feed forward Neural Networks

19 / 5

Back Propagation

19 / 5

Stochastic Gradient Descent

20 / 6

Convolutional Neural Networks

20 / 6

Convolutional Neural Networks

21 / 7

Medical Imaging

21 / 7

Medical Imaging

22 / 8

Clustering and k-means

22 / 8

Gaussian Mixture Models and the Expectation Maximization algorithm

23 / 9

Principle Components Analysis

23 / 9

Autoencoders

24 / 10

t-SNE

24 / 10

Latent Variable Models and missing data

25 / 11

Expectation Maximization algorithm revisited

25 / 11

Variational Inference

26 / 12

Stochastic Variational Inference

26 / 12

Variational Autoencoder

27 / 13

Generative Adversarial Models

27 / 13

Generative Adversarial Models

28 / 14

 

28 / 14

Open Topics, Final Exam Preparation

29 / 15

 

29 / 15

Final Exam

 

supervised learning

 

unsupervised learning

Leistungserfassung

The final grade is based 100% on the final written exam.

Processing of regular exercise sheets (every one to two weeks) is required for a Klausur approval.

Termine

  • Lecture #1:  Monday 15:15-16:45
  • Lecture #2: Tuesday 9:15-10:45
  • Tutorials: Time and place will be arranged jointly with students during the first lecture.

Zurück