{"id":206,"date":"2020-11-16T19:51:33","date_gmt":"2020-11-16T19:51:33","guid":{"rendered":"http:\/\/www.peter-zaspel.de\/?p=206"},"modified":"2021-09-19T21:05:55","modified_gmt":"2021-09-19T21:05:55","slug":"machine-learning-spring-2020","status":"publish","type":"page","link":"https:\/\/www.peter-zaspel.de\/?page_id=206","title":{"rendered":"Machine Learning (Spring 2020)"},"content":{"rendered":"\n

Overview<\/h3>\n\n\n\n

Official course description<\/h4>\n\n\n\n

Machine learning (ML) is about algorithms which are fed with (large quantities of) real-world data, and which return a compressed “model” of the data. An example is the “world model” of a robot: the input data are sensor data streams, from which the robot learns a model of its environment — needed, for instance, for navigation. Another example is a spoken language model: the input data are speech recordings, from which ML methods build a model of spoken English — useful, for instance, in automated speech recognition systems. There exist many formalisms in which such models can be cast, and an equally large diversity of learning algorithms. However, there is a relatively small number of fundamental challenges which are common to all of these formalisms and algorithms. The lecture introduces such fundamental concepts and illustrates them with a choice of elementary model formalisms (linear classifiers and regressors, radial basis function networks, clustering, neural networks, hidden Markov models). Furthermore, the lecture also provides a refresher of required mathematical material from probability theory and linear algebra.<\/p>\n\n\n\n

Literature<\/h4>\n\n\n\n

Primary text<\/strong>:
Hastie, Tibshirani, Friedman: \u201cThe Elements of Statistical Learning\u201d (Second Edition), Springer<\/p>\n\n\n\n

Recommended reading<\/strong>:
Shalev-Shwartz, Ben-David: \u201cUnderstanding Machine Learning: From Theory to Algorithms\u201d, Cambridge University Press<\/p>\n\n\n\n

Further useful references for the math background:
<\/strong>Linear algebra and probability reviews available at http:\/\/cs229.stanford.edu\/syllabus.html<\/a> <\/p>\n\n\n\n

Grading<\/h4>\n\n\n\n

The grades for this lecture will be determined as follows:<\/p>\n\n\n\n