Lehrinhalte
Machine learning is the science of making computers act without being explicitly programmed. Over the past decade, machine learning has enabled us to drive self-propelled cars, perform practical speech recognition, perform effective web searches and significantly improve our understanding of the human genome. Machine learning is so ubiquitous today that people probably use it dozens of times a day without knowing it. Many researchers also believe that it is the best way to make progress towards AI on the human level. In this course you will learn the most effective techniques of machine learning.
More importantly, you will not only learn the theoretical principles of machine learning, but also acquire the practical know-how needed to quickly apply these techniques to new problems.
This course provides a comprehensive introduction to machine learning, data mining and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practice in machine learning (distortion/variance theory). The course will also draw on numerous case studies and applications related to construction, so you will also learn how to apply learning algorithms to building intelligent control, text comprehension, computer vision, and other areas.
Literatur
Hands-on machine learning with Scikit-Learn, Keras and Tensorflow Aurelien Geron
Künstliche Intelligenz für Ingenieure Jan LunzeScikit-Learn Cookbook Julian Avila
Voraussetzungen
Mathematics 1-3
English knowledge
Machine learning is the science of making computers act without being explicitly programmed. Over the past decade, machine learning has enabled us to drive self-propelled cars, perform practical speech recognition, perform effective web searches and significantly improve our understanding of the human genome. Machine learning is so ubiquitous today that people probably use it dozens of times a day without knowing it. Many researchers also believe that it is the best way to make progress towards AI on the human level. In this course you will learn the most effective techniques of machine learning.
More importantly, you will not only learn the theoretical principles of machine learning, but also acquire the practical know-how needed to quickly apply these techniques to new problems.
This course provides a comprehensive introduction to machine learning, data mining and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practice in machine learning (distortion/variance theory). The course will also draw on numerous case studies and applications related to construction, so you will also learn how to apply learning algorithms to building intelligent control, text comprehension, computer vision, and other areas.
Literatur
Hands-on machine learning with Scikit-Learn, Keras and Tensorflow Aurelien Geron
Künstliche Intelligenz für Ingenieure Jan LunzeScikit-Learn Cookbook Julian Avila
Voraussetzungen
Mathematics 1-3
English knowledge
- Lehrende: Hagen Berthold
- Lehrende: Henrik Riedel
- Lehrende: Jens Schneider
Semester: Inverno 2020/21