Undergraduate

Intelligent Systems

Compulsory course for Third Year students of the Faculty of Computer Systems. Offered in Spring.

Prerequisites: Artificial Intelligence

Course content

Quantifying uncertainty

acting under uncertainty, inference using full joint distributions, variable independence, Bayes rule, probabilistic puzzles

Probabilistic reasoning I

Bayesian networks (BNs), global and local semantics, constructing BNs, Markov blanket, d-separation algorithm, deterministic nodes, noisy-or

Probabilistic reasoning II

exact inference (enumeration, variable elimination), approximate inference (rejection sampling, likelihood weighting), markov chains

Probabilistic reasoning over time I

time and uncertainty, inference in temporal models

hidden Markov models, Kalman filters, dynamic Bayesian networks, Viterbi algorithm

Making simple decisions

utility theory, utility functions, decision networks, the value of information, cognitive biases

Making complex decisions

sequential decision problems, value iteration, policy iteration, partially observable Markov Decision Processes, game theory, mechanism design

Supervised learning

regression and classification, decision trees, regression trees, learning probabilistic models, Naive Bayes, learning with hidden variable, support vector machines, ensemble learning

Artificial neural networks

perceptrons, multilayer perceptrons, backpropagation, deep learning (DL), convolutional neural networks, recurrent neural networks; applications of DL

Knowledge in learning

explanation-based learning, learning using relevance information, inductive logic programming, version spaces, explainable AI (XAI)

Unsupervised learning I

datamining, cluster analysis, partitional clustering, k-means, bisecting k-means, hierarchical clustering, cluster similarity

Unsupervised learning II

frequent itemset generation, rule generation, compact representation of frequent itemsets, sequential pattern mining

Reinforcement learning (RL)

passive RL, active RL, policy search, applications of RL

Natural language processing

machine comprehension, augmented grammars and semantic representation, text classification, AI ethics

Main bibliography

Russell, Stuart J., and Peter Norvig. Artificial intelligence: a modern approach. 4th edition, 2020

Additional bibliography

Finn Verner Jensen and Nielsen, Thomas Dyhre, Bayesian networks and decision graphs. 2nd edition, Springer, 2016
Tan, Pang-Ning, Michael Steinbach, and Vipin Kumar. Introduction to data mining. Pearson Education, 2016
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521, no. 7553 (2015): 436-444