Artificial Intelligence

PROGRAM CORE

Credit hour: 3

Pre-requisite: Discrete Mathematics ; Algorithms and Data Structure

Synopsis

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm. The students will learn to build intelligent systems that efficiently make decisions in fully informed, partially observable, and adversarial settings. Searching in a complex environment will be covered by this course that includes local search; optimization problems; local search in continuous space, and the constraint satisfaction problem. Adversarial searching and games theory concepts such as Monte-Carlo Tree Search will also be discussed in this course. Knowledge representation and reasoning based on probability such as Bayes rule, Bayesian Networks, causal inference, and Hidden Markov Models will be covered in this course. Basic machine learning and deep learning concepts will also be discussed with an emphasis on supervised learning algorithms for regression and classification. At the end of this course, the student will grasp the basic concepts of artificial intelligence such as intelligent searching for complex problem solving, machine learning, and deep learning that are sufficient enough for them to identify the suitable approach in solving specific problems. The knowledge they learn in this course will serve as the foundation for further study in any application area they choose to pursue.

Course Content

Part 1 Artificial Intelligence Overview ( 1 week)

Introduction to Artificial Intelligence
Intelligent Agents
The Future of AI - AI components and AI architecture

Part 2 Artificial Intelligence Programming ( 1 week)

AI Programming Tools and Language
Framework and Libraries for AI Programming

Part 3 Problem Solving (6 weeks)

Solving Problems by Searching - search algorithms, greedy algorithms, uninformed search strategies, heuristic search strategies, and heuristic function.
Search in Complex Environments: Local search and optimization problems (hill-climbing, simulated annealing, local beam search, and evolutionary algorithms)
Constraint Satisfaction Problems - inference for CSP, backtracking search, and local search for CSP.
Adversarial Search and Games - Game theory, Monte Carlo Tree Search

Part 4 Knowledge representation and reasoning (3 weeks)

Quantifying Uncertainty - inference using full joint probability, Bayes rules, Naive Bayes Models.
Probabilistic Reasoning - knowledge representation in an uncertain domain, Bayesian Network, inference in Bayesian networks, and Causal Networks.
Probabilistic Reasoning Over Time - Hidden Markov Models

Part 5 Introduction to Machine Learning (2 weeks)

Forms of Learning
Supervised Learning
Decision Trees
Linear Regression and Classification
Simple Feedforward Network
Basic Deep Learning

Part 5 Philosophy, Ethics and Safety of AI (1 week)

References

Russell, S. J., Norvig, P., & Davis, E. (2020). Artificial intelligence: a modern approach. 4th ed. Upper Saddle River, NJ: Prentice Hall.

Prepared By

Assoc. Prof. Ts Dr. Amiza Amir

Page updated

Report abuse