Objectives: Modern machine learning techniques are proving to be extremely valuable for the analysis of data in computational biology problems. This course provides an introduction to many concepts, techniques, and algorithms in machine learning such as classification and linear regression and ending up with more recent topics such as support vector machines. The students will learn the fundamental concepts and modern machine learning methods as well as a more formal understanding. The underlying theme in the course is statistical inference as it provides the foundation for most of the methods covered. The students apply the knowledge on examples from biological data and techniques considering real biological examples.
Program
Module 1. Introduction
- Philosophy
- Machine learning (ML)
- Need in Computational Biology
- Review of probability theory
- Basic concepts in machine learning
Module 2. Unsupervised and Reinforced Learning
- K-means and Gaussian Mixture Models
- K-Nearest Neighbors and Bayesian Classifiers
- Classification and Regression Trees (CART) & Random Forest
- Neural Networks
Module 3. Supervised and Reinforced Learning
- Regression
- Logistic Regression
- Support Vector Machines
- The kernel trick
- Neural Networks
- Monte Carlo inference
- Bayesian Inference
Module 4. Kernel methods in system identification
- Reproducing Kernel Hilbert Spaces
- Parametric model structures
- Regularized least squares method
- Selection of model flexibility: AIC, BIC, CV
- Marginal likelihood maximization
- Parameter estimation of biological models
Previous Courses: Otto-von-Guericke-Universität Magdeburg (Winter 2016)
Next Course: Otto-von-Guericke-Universität Magdeburg (Winter 2017)