2014 - 2015

0572-5350-01
  Selected Topics in Industrial Eng:Advanced Probabilistic Too                                         
FACULTY OF ENGINEERING
Prof. Yigal GerchakComputer and Software Engineering106Mon1700-1900 Sem  1
 
 
University credit hours:  2.0

Course description
Lecture: 2 hours
 
Overview: foundations, scope, problems, and approaches of AI.
From brain models of technology: perceptron, feedforward neural networks, recurrent neural
networks, neural models of memory, neural models of clustering, learning methods with neural
networks, practical applications with artificial neural networks.
From neurons to Intelligent agents: reactive, deliberative, goal-driven, utility-driven, and
learning agents
Problem-solving through Search: forward and backward, state-space, blind, heuristic, problemreduction,
A, A*, AO*, minimax, constraint propagation, neural, stochastic, and evolutionary
search algorithms, sample applications.
Knowledge Representation and Reasoning: ontologies, foundations of knowledge
representation and reasoning, representing and reasoning about objects, relations, events, actions,
time, and space; predicate logic, situation calculus, description logics, reasoning with defaults,
reasoning about knowledge, sample applications.
Planning: planning as search, partial order planning, construction and use of planning graphs
Representing and Reasoning with Uncertain Knowledge: probability, connection to logic,
independence, Bayes rule, bayesian networks, probabilistic inference, sample applications.
The following will be fast learnt in class and groups will take topics with projects:
Machine Learning and Knowledge Acquisition: classifiers, clustering techniques. Include
based on time permitting exploration, nearest neighbor, decision tree classifiers, Q-learning,
multi-agent systems, support vector machines, support vector clustering.
Sample Applications of AI, student project presentations.
The text for the course are:
1. Artificial Intelligence: A Modern Approach, 3rd Edition, by Stuart Russell and Peter Norvig.,
2. Neural Networks: A Comprehensive Foundation (2nd Edition) by Simon Haykin OR Neural
Networks and Learning Machines (3rd Edition) by Simon Haykin
The course will often draw upon a variety of additional readings to supplement the treatment of
topics available in the primary textbook.
 

accessibility declaration


tel aviv university