|
|
|
||
|
The introductory course on artificial intelligence with the stress on
basic concepts and methods. Attention is paid to theoretical background (problem
solving, knowledge representation, theorem proving, reasoning under uncertainty)
so as to some application areas (perception, natural language processing,
plan generation, machine learning).
Last update: T_KTI (16.05.2003)
|
|
||
|
S. Russell, P. Norvig: Artificial Intelligence; A Modern Approach, 1995
V. Mařík, O. Štěpánková, J. Lažanský a kol.: Umělá Inteligence (1). Academia, Praha
V. Mařík, O. Štěpánková, J. Lažanský a kol.: Umělá Inteligence (2). Academia, Praha
F.V. Jensen: Bayesian Networks and Decision Graphs
T. Mitchell: Machine Learning
Havel I.M.: Robotika. SNTL Praha, 1980
Renc Z.: Vybrané partie z umělé inteligence. Skriptum MFF UK Praha, 1987
V. Mařík, O. Štěpánková, J. Lažanský a kol.: Umělá Inteligence (3). Academia, Praha Last update: T_KTI (15.05.2003)
|
|
||
|
1 History of AI: Turing test, MYCIN, Eliza, production systems
2 Solving problems by searching (A* algorithm, IDA*, Branch and bound, AND/OR graphs)
3 Games (Minimax, Alpha-Beta Pruning, nondeterministic games)
4 Knowledge representation (semantic networks, frame systems, first-order logic)
5 Resolution
6 Planning (situation calculus, STRIPS, partial-order planning, hierarchical decomposition)
7 Uncertain knowledge and reasoning (Bayesian networks, Dempster-Shafer theory, Markov processes)
8 Machine learning (decision trees, concept learning as search, neural networks, genetic algorithms)
9 Perception (image processing, scene analysis, speech recognition, natural language processing) Last update: T_KTI (16.05.2003)
|