Back to Modules
CS420

Introduction to Artificial Intelligence

1 CreditsBoth

Description

Artificial Intelligence (Artificial Intelligence) aims to augment or substitute human intelligence in solving complex real world decision making problems. This is a breadth course that will equip students with core concepts and practical know-how to build basic AI applications that impact business and society. Specifically, we will cover search (e.g., to schedule meetings between different people with different preferences), probabilistic graphical models (e.g. to build an AI bot that evaluates whether credit card fraud has happened based on transactions), planning and learning under uncertainty (e.g., to build AI systems that guide doctors in recommending medicines for patients or taxi drivers to “right\" places at the “right\" times to earn more revenue), multi-agent systems (e.g., to build next generation patrolling systems for critical infrastructure security), image processing (e.g. to build systems that track and/or recognize suspicious people) and natural language processing (e.g., to build chat bots that can automatically and intelligently interact with customers in different service industries).

Requisites

Prerequisites: IS111/IS200/SMT111/COR-IS1704/(CS101&CS201) - Pre-req

Co-requisites: None

Anti-requisites: None

Attributes

Department: SCIS

Course Level: Undergraduate

Tracks: CS/IS: Artificial Intelligence Track IS Major: Software Development Track IS/T4BS: Business Analytics Track

Areas: Advanced Business Technology Major Analytics Major Business Options Data Science and Analytics Electives Econ Major Rel/Econ Options Grad Req - Dig Tech/Data Ana (Intake 2024 onwards) IS Depth Electives Social Sciences/PLE Major-related

Learning Outcomes

1. Representing knowledge associated with a domain using Bayesian Networks and performing inference on them using tools 2. Solve classification problems associated with images using Deep Neural Networks 3. Make multi-stage decisions in problems with uncertainty using MDPs and Reinforcement Learning 4. Performing sentiment analysis on natural language data using Deep Neural Networks

Graduate Learning Outcomes

Disciplinary Knowledge, Critical thinking & problem solving, Collaboration and leadership, Communication, Self-directed learning

Competencies

Data Analytics, Combinatorial Decision-making, Computer Vision Technology, Intelligent Reasoning, Text Analytics and Processing