PV021 Neural Networks

Faculty of Informatics
Autumn 2022
Extent and Intensity
2/0/2. 4 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium).
Taught in person.
Teacher(s)
doc. RNDr. Tomáš Brázdil, Ph.D. (lecturer)
Mgr. Tomáš Foltýnek, Ph.D. (assistant)
Mgr. Matej Gallo (assistant)
Mgr. Adam Bajger (assistant)
Mgr. Adam Ivora (assistant)
Mgr. Andrej Kubanda (assistant)
Mgr. Tomáš Repák (assistant)
Mgr. Petr Zelina (assistant)
Guaranteed by
doc. RNDr. Tomáš Brázdil, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Contact Person: doc. RNDr. Tomáš Brázdil, Ph.D.
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics
Timetable
Thu 8:00–9:50 D3, except Thu 3. 11. ; and Thu 3. 11. 8:00–9:50 A318
Prerequisites
Recommended: knowledge corresponding to the courses MB102 and MB103.
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
there are 75 fields of study the course is directly associated with, display
Course objectives
Introduction to neural networks.
Learning outcomes
At the end of the course student will have a comprehensive knowledge of neural networks and related areas of machine learning. Will be able to independently learn and explain neural networks problems. Will be able to solve practical problems using neural networks techniques, both independently and as a part of a team. Will be able to critically interpret third party neural-networks based solutions.
Syllabus
  • Basics of machine learning and pattern recognition: classification and regression problems; cluster analysis; supervised and unsupervised learning; simple examples
  • Perceptron: biological motivation; geometry
  • Linear models: least squares (pseudoinverse, gradient descent, Widrow-Hoff rule); connection with Bayes classifier; connection with maximum likelihood; regularization; bias-variance decomposition
  • Multilayer neural networks: multilayer perceptron; loss functions; backpropagation
  • Practical considerations: basic data preparation; practical techniques for improving backpropagation; bias & variance tradeoff; overfitting; feature selection; applications
  • Hopfield network: Hebb's rule; energy; capacity
  • Deep learning: restricted Boltzmann machines (sampling, maximum-likelihood learning, contrastive divergence learning); learning in deep neural networks (vanishing gradient, pretraining with autoencoders, deep belief networks)
  • Convolutional networks
  • Recurrent networks: Elman and Jordan networks, LSTM
  • Clustering: density estimation; self-organizing maps
  • Project: Software implementation of particular models and their simple applications.
Literature
    recommended literature
  • GOODFELLOW, Ian, Yoshua BENGIO and Aaron COURVILLE. Deep Learning. MIT Press, 2016. info
    not specified
  • ŠÍMA, Jiří and Roman NERUDA. Teoretické otázky neuronových sítí. Vyd. 1. Praha: Matfyzpress, 1996, 390 s. ISBN 80-85863-18-9. info
  • KOHONEN, Teuvo. Self-Organizing Maps. Berlin: Springer-Verlag, 1995, 392 pp. Springer Series in Information Sciences 30. ISBN 3-540-58600-8. info
Teaching methods
Theoretical lectures, group project
Assessment methods
Lectures, class discussion, projects. Several midterm progress reports on the respective projects, one final project presentation plus oral examination.
Language of instruction
English
Further Comments
Study Materials
The course is taught annually.
Listed among pre-requisites of other courses
The course is also listed under the following terms Spring 2003, Spring 2004, Spring 2005, Spring 2007, Spring 2009, Spring 2011, Spring 2012, Spring 2013, Spring 2014, Autumn 2015, Autumn 2016, Autumn 2017, Autumn 2018, Autumn 2019, Autumn 2020, Autumn 2021, Autumn 2023, Autumn 2024.
  • Enrolment Statistics (Autumn 2022, recent)
  • Permalink: https://is.muni.cz/course/fi/autumn2022/PV021