Machine Learning 2
Code  Completion  Credits  Range  Language 

BIML2.21  Z,ZK  5  2P+2C  Czech 
 Garant předmětu:
 Daniel Vašata
 Lecturer:
 Daniel Vašata
 Tutor:
 Daniel Vašata
 Supervisor:
 Department of Applied Mathematics
 Synopsis:

The goal of this course is to introduce students to the selected advanced methods of machine learning. In the supervised learning scenario, they, in particular, learn kernel methods and neural networks. In the unsupervised learning scenario students learn the principal component analysis and other dimensionality reduction methods. Moreover, students get the basic principles of reinforcement learning and natural language processing.
 Requirements:

The knowledge of calculus, linear algebra and probability theory is assumed. Furthermore, the knowledge of machine learning corresponding to topics covered in the course BIEML1 is also assumed.
 Syllabus of lectures:

1. Linear basis expansion, Kernel regression
2. Support vector machines for classification
3. Dimensionality reduction  Principal component analysis
4. Dimensionality reduction  Linear discriminant analysis, Locally linear embedding
5. Generative models  Naive Bayes
6. Neural Networks  Perceptron, multilayer perceptron, deep learning
7. Neural Networks  backpropagation, regularization
8. Neural Networks  convolutional neural networks
9. Neural networks  recurrent neural networks, modern trends
10. Reinforcement learning  introduction, multiarmed bandit
11. Reinforcement learning  Markov decision processes
12. Natural language processing
 Syllabus of tutorials:

1. Linear basis expansion, Kernel regression
2. Support vector machines
3. Dimensionality reduction  Principal component analysis
4. Dimensionality reduction  Linear discriminant analysis, Locally linear embedding
5. Generative models  Naive Bayes
6. Neural Networks  Perceptron, multilayer perceptron
7. Neural Networks  deep learning, regularization
8. Neural Networks  convolutional neural networks
9. Neural networks  recurrent neural networks
10. Reinforcement learning I
11. Reinforcement learning II
12. Natural language processing
 Study Objective:

The course aims to introduce students to more advanced methods of a rapidly developing field of machine learning.
 Study materials:

1. Hastie T., Tibshirani R., Friedman, J. : The Elements of Statistical Learning. Springer, 2009. ISBN 9780387848570.
2. Goodfellow I., Bengio Y., Courville A. : Deep Learning. MIT Press, 2016. ISBN 9780262035613.
3. Sutton R. S., Barto A. G. : Reinforcement Learning. MIT Press, 2018. ISBN 9780262039246.
 Note:
 Further information:
 https://courses.fit.cvut.cz/BIML2/
 Timetable for winter semester 2023/2024:
 Timetable is not available yet
 Timetable for summer semester 2023/2024:
 Timetable is not available yet
 The course is a part of the following study plans:

 Bachelor specialization Information Security, in Czech, 2021 (elective course)
 Bachelor specialization Management Informatics, in Czech, 2021 (elective course)
 Bachelor specialization Computer Graphics, in Czech, 2021 (elective course)
 Bachelor specialization Computer Engineering, in Czech, 2021 (elective course)
 Bachelor program, unspecified specialization, in Czech, 2021 (VO)
 Bachelor specialization Web Engineering, in Czech, 2021 (elective course)
 Bachelor specialization Artificial Intelligence, in Czech, 2021 (PS)
 Bachelor specialization Computer Science, in Czech, 2021 (elective course)
 Bachelor specialization Software Engineering, in Czech, 2021 (elective course)
 Bachelor specialization Computer Systems and Virtualization, in Czech, 2021 (elective course)
 Bachelor specialization Computer Networks and Internet, in Czech, 2021 (compulsory elective course, elective course)