CSPB 3202 - Introduction to Artificial Intelligence
*Note: This course description is only applicable for the Computer Science Post-Baccalaureate program. Additionally, students must always refer to course syllabus for the most up to date information.
- Credits: 3.0
- Prerequisites: Prerequisite of CSPB/CSCI 2270, CSPB/CSCI 2824, and CSPB/CSCI 3022, all with minimum grade C-.
- Minimum Passing Grade: C-
- Textbook: Artificial Intelligence: A Modern Approach 3rd Ed. by Peter Norvig and Stuart J. Russell
[video:https://youtu.be/kOLYgiz2B_I]
Brief Description of Course Content
Surveys artificial intelligence techniques of search, knowledge representation and reasoning, probabilistic inference, machine learning, and natural language.
Specific Goals for the Course
- An ability to explain what AI is about, what it can solve, its brief history and applications, and its social impact.
- An ability to explain key concepts such as agents, environment and how the type of the agent and the environment affect the choice of an algorithm
- An ability to explain how each AI algorithm works and implement those in codes.
- An ability to explain the algorithm properties such as completeness, optimality, time and space complexity and can compare algorithm efficiencies.
- Determine suitable AI algorithms to apply to a specific problem.
- Search
- Classical search: DFS, BPS, iterative deepening, UCS
- Non-classical search: heuristics, greedy search, A*
- CSP
- Adversarial Search
- Probabilistic Search
- MDP
- Reinforcement Learning
- BayesNets, HMM
- Machine learning in AI
- Machine learning basics
- Logistic regression, perceptron, ANN, other ML models (e.g. decision tree)
- Deep learning, applications in computer vision, NLP, robotics
Data Structures: Queue, stack, tree, graph
Probability Basics: Bayes Rule, conditional probability, joint probability
Basic Math Functions: Logarithm, exponent, argmax/argmin, max/min
Basic Calculus: concept of partial differentiation, gradient, chain rule