Program Overview

---

Introduction to Machine Learning

The course "Introduction to Machine Learning" is offered by ETH Zurich, taught by Prof. Andreas Krause, and took place in the Autumn Semester of 2013.

Course Description

Machine learning algorithms are data analysis methods that search data sets for patterns and characteristic structures. Typical tasks include the classification of data, automatic regression, and unsupervised model fitting. Machine learning has emerged mainly from computer science and artificial intelligence, drawing on methods from various related subjects, including statistics, applied mathematics, and more specialized fields such as pattern recognition and neural computation. Applications include image and speech analysis, medical imaging, bioinformatics, and exploratory data analysis in natural science and engineering.

This course is intended as an introduction to machine learning, reviewing the necessary statistical preliminaries and providing an overview of commonly used machine learning methods. Further and more advanced topics are discussed in the course Statistical Learning Theory, held in the spring semester by Prof. Buhmann.

General Information

Time and Place

• Lectures
  • Mon: 14-15, CAB G11
  • Tue: 10-12, CAB G11
• Tutorials
  • Wed: 15-17, CAB G61, Last Names A-E
  • Thu: 15-17, CAB G59, Last Names F-K
  • Fri: 08-10, CAB G52, Last Names L-R
  • Fri: 13-15, CHN G46, Last Names S-Z All tutorial sessions are identical; please only attend one session.

Syllabus

The syllabus includes the following topics:

• Introduction to Machine Learning
• Regression
• Cross-validation
• Perceptron
• SVMs
• Nonlinear SVMs
• Kernels
• k-NN
• Sparsity
• Multiclass
• Structured prediction
• Probabilistic modeling
• Logistic regression
• Bayesian learning
• Gaussian processes
• Ensemble methods
• Discriminative vs. Generative models
• Clustering
• k-Means
• GMMs
• Dimension reduction
• (K)-PCA
• LLE
• MDS

Exercises

The exercise problems include theoretical and programming problems. It is not mandatory to submit solutions, and a Testat is not required to participate in the exam. Exercise solutions are published after one week.

Project

Part of the coursework is a project carried out in groups of up to 3 students. The goal of this project is to gain hands-on experience in machine learning tasks. The project grade constitutes 30% of the total grade.

Exam

The mode of examination is written, with a 120-minute length. The language of examination is English. As written aids, you can bring two A4 pages (i.e., one A4 sheet of paper), either handwritten or 11-point minimum font size. The written exam constitutes 70% of the total grade.

Resources

Text Books

• C. Bishop. Pattern Recognition and Machine Learning. Springer 2007.
• R. Duda, P. Hart, and D. Stork. Pattern Classification. John Wiley & Sons, second edition, 2001.
• T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, 2001.
• L. Wasserman. All of Statistics: A Concise Course in Statistical Inference. Springer, 2004.

Matlab

The official Matlab documentation is available online at the Mathworks website. If you have trouble accessing Matlab's built-in help function, you can use the online function reference or the command-line version. There are several primers and tutorials on the web, including the book Matlab Primer by T. Davis and K. Sigmon, CRC Press, 2005.