Machine Learning 2

Course guarantor:

Lecturer:

Tutor:

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 BIE-ML1 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, multi-layer 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, multi-armed 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, multi-layer 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 978-0-387-84857-0.

2. Goodfellow I., Bengio Y., Courville A. : Deep Learning. MIT Press, 2016. ISBN 978-0-262-03561-3.

3. Sutton R. S., Barto A. G. : Reinforcement Learning. MIT Press, 2018. ISBN 978-0-262-03924-6.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Bachelor Specialization Computer Networks and Internet, part-time, in Czech, 2021 (compulsory elective course)