Subjects

Your browser does not support JavaScript, or its support is disabled. Some features may not be available.

Nature Inspired Algorithms - NAIL119

Title:	Přírodou inspirované algoritmy
Guaranteed by:	Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Faculty:	Faculty of Mathematics and Physics
Actual:	from 2021
Semester:	summer
E-Credits:	5
Hours per week, examination:	summer s.:2/2, C+Ex [HT]
Capacity:	unlimited
Min. number of students:	unlimited
4EU+:	no
Virtual mobility / capacity:	no
State of the course:	taught
Language:	Czech, English
Teaching methods:	full-time
Additional information:	http://ktiml.mff.cuni.cz/~pilat/cs/prirodou-inspirovane-algoritmy/

Guarantor:	doc. Mgr. Martin Pilát, Ph.D.
Teacher(s):	Mgr. Gabriela Kadlecová Mgr. Matyáš Lorenc doc. Mgr. Martin Pilát, Ph.D.
Class:	Informatika Bc.
Classification:	Informatics > Informatics, Software Applications, Computer Graphics and Geometry, Database Systems, Didactics of Informatics, Discrete Mathematics, External Subjects, General Subjects, Computer and Formal Linguistics, Optimalization, Programming, Software Engineering, Theoretical Computer Science
Is incompatible with:	NAIL115
Is interchangeable with:	NAIL115

Opinion survey results Examination dates Noticeboard

Annotation -

The goal of the lecture is to introduce the main nature-inspired algorithms (evolutionary algorithm, neural networks, …) and how they can be applied to solve problems in optimization and machine learning. In the seminar, some of the algorithms will be implemented and used to solve simple problems in the areas mentioned above.

Last update: Hric Jan, RNDr. (27.04.2018)

Aim of the course -

Introduce the basics of nature-inspired algorithms used in machine learning and optimization (evolutionary algorithms, neural networks, etc.).

Last update: Hric Jan, RNDr. (27.04.2018)

Course completion requirements -

In order to pass the course, the student must obtain the credit for the seminar and pass an exam. The credit is given for solving assignments from the seminar. The nature of study verification excludes the possibility of its repetition.

Last update: Hric Jan, RNDr. (27.04.2018)

Literature -

1. Olarius S., Zomaya A. Y., Handbook of Bioinspired Algorithms and Applications, Chapman & Hall/CRC, 2005. ISBN: 978-1-584-88475-0

2. de Castro, L. N., Fundamentals of Natural Computing: Basic Concepts, Algorithms, and Applications, CRC Press, 2006. ISBN: 978-1-584-88643-3

3. Eiben, A.E and Smith, J.E.: Introduction to Evolutionary Computing, (2nd ed), Springer-Verlag, 2015. ISBN: 978-3-662-44874-8

4. Poli R., Langdon W. B., McPhee, N. F., A Field Guide to Genetic Programming. Lulu.com, 2008 ISBN: 978-1-409-20073-4

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

Last update: Hric Jan, RNDr. (27.04.2018)

Requirements to the exam -

The exam is oral with time for written preparation. The requirements correspond to the syllabus in the extent presented during the lectures. A part of the exam may be the design of an algorithm for a given problem.

Last update: Hric Jan, RNDr. (27.04.2018)

Syllabus -

Biological inspiration in the design of algorithms and models

a. evolutionary models

b. neural models

Evolutionary algorithms

a. Simple genetic algorithm

b. Representation, genetic operators, fitness, selection

c. Evolutionary algorithms for continuous optimization

d. Neuro-evolution, algorithm NEAT

e. Genetic programming

Swarm algorithms

a. Ant Colony Optimization

b. Particle Swarm Optimization

Neural networks

a. Perceptron, multi-layered perceptron, back-propagation as a learning algorithm

b. Convolutional networks

c. RBF networks a Kohonen’s maps

Other nature inspired algorithms

a. Artificial Immune Systems

b. Cellular Automata

c. Artificial Life

Applications in optimization and machine learning

a. Continuous and combinatorial optimization

b. Multi-objective optimization

c. Supervised and unsupervised learning, reinforcement learning

Last update: Hric Jan, RNDr. (27.04.2018)