1. SylabUZ
2. Faculty of Computer Science, Electrical Engineering and Automatics
3. winter term 2017/2018
4. Computer Science - Erasmus programme
5. Elements of artificial intelligence

Generate PDF for this page

Elements of artificial intelligence - course description

Aim of the course

• Familiarize students with the concept of artificial neural networks and their learning algorithms,
• Familiarize students with the concept of fuzzy sets and fuzzy inference mechanism,
• Familiarize students with different graph search strategies.
• Teach students to solve practical engineering problems using artificial intelligence methods.

Prerequisites

Save changes

Principles of programming, Algorithms and data structures

Scope

Artificial neural networks.Biological neuron. Mathematical model of a neuron. Simple
perceptron. Perceptron learning rule. Perceptron limitations. Models of neurons and their properties. Adaline and Madaline architectures. Multilayer neural networks. Learning of single-layer neural network. Learning of multi-layer neural network. Error back propagation algorithm. Models of dynamic neurons. Dynamic neural networks. Sample applications of artificial neural networks.

Fuzzy sets and neuro-fuzzy systems. Fuzzy sets anf fuzzy logic. Operations on fuzzy sets. Fuzzy inference. Fuzzy rules. Neuro-fuzzy structures and learning algorithms. Sample applications of fuzzy systems.

Graph search strategies. The breadth first search algorithm. The depth first search algorithm. The A* search algorithm. Heuristic functions. Memory and time compelxity. The minimax algorithm. The alpha-beta pruning algorithm. Constrained search.

Teaching methods

Lecture, teaching laboratory classes.

Learning outcomes and methods of theirs verification

Outcome description	Outcome symbols	Methods of verification	The class form

Assignment conditions

Lecture - the passing criterion is a sufficient mark from the final test.
Laboratory - the passing criterion are positive marks for laboratory exercises and tests.
Final mark components = lecture: 50% + teaching laboratory: 50%

Recommended reading

1. Russell S., Norvig P.: Artificial Intelligence: A Modern Approach, Prentice Hall, 2009.
2. Bishop C.M., Hinton G. : Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
3. Edelkamp S., Schroedl S.: Heuristic Search: Theory and Applications, Morgan Kaufmann, 2012. 
4. Zimmermann H-J.: Fuzzy Set Theory and Its Applications, Springer, 2006.

Further reading

1. Bishop C.: Pattern Recognition and Machine Learning, Springer Verlag, 2006.
2. Goodfellow I., Bengio Y., Courville A.: Deep Learning, MIT Press, 2016.
3. Ross. T.: Fuzzy Logic with Engineering Applications, Wiley, 2004.

Notes

Modified by dr hab. inż. Marek Kowal, prof. UZ (last modification: 05-05-2017 12:59)