Course description
An introduction to the basic principles, techniques, and applications of Artificial Intelligence. Coverage includes perception and learning, searching and logical inference and knowledge base. Methods used in this course will have wide applications in different artificial intelligent systems such as expert system, robotics, computer vision, and natural language processing. Students will have practical experience in designing and implementing components of an intelligent system.
Course objective
- Become familiar with basic principles of AI toward problem solving
- Understanding the basics of machine learning
- Experiment with tools and writing code for developing different aspects of intelligent systems
Course content
a. Intelligent Agents and Environment
b. Discrete Optimization – Search based methods
c. Constraint Discrete Optimization – Constraint Satisfaction Search
d. Local Search Methods
e. Logic and Inference
f. Continuous Optimization – Gradient Descent and Introduction to Machine Learning
g. Neural Networks
Learning outcomes
- CLO1: Ability to understand different types of AI agents and its components and search-based optimization in discrete state-spaces
- CLO2: Apply search based methods, logical reasoning and machine learning to solve problem
- CLO3: Using tools, libraries to design and implement components of a learning agent. They should be able to use modern languages appropriate for AI systems such as Python – NumPy, PyTorch library to write code.
Topics
Week | Topic | Teaching-Learning Strategy | Assessment Strategy | Corresponding CLOs |
|---|---|---|---|---|
1 | Intelligent agents: a discussion on what Artificial Intelligence is about and different types of AI agents. | Lecture (3h) | Class Test Assignment | CLO1 |
2 | Understanding the ethical aspects of AI and Introduction to searching | Lecture (3h) | Class Test Assignment Midterm Exam | CLO1 |
3 | Optimization on a Discrete state-space - Uninformed and informed search methods – BFS, DFS, IDS, A*, and IDA* search methods | Lecture (3h) | Assignment Midterm Exam | CLO2 |
4 | Searching – Branch and Bound, cycle checking, multi-path pruning, Beam search | Lecture (3h) | Midterm Exam | CLO2 |
5 | Searching – continued, Introduction to Constraint Satisfaction Search - Backtracking | Lecture (3h) | Assignment Midterm Exam | CLO2 |
6 | Constraint Satisfaction Search – Forward Checking and Arc Consistency | Lecture (3h) | Assignment Midterm Exam | CLO2 |
7 | Local Search Methods - Hill Climbing, Simulated Annealing, Genetic algorithms, Swarm intelligence – Particle Swarms, Ant Colony Optimization | Lecture (3h) | Assignment Midterm | CLO2 |
8 | Logical Reasoning - Propositional logic, Reasoning - Forward and Backward Chaining | Lecture (3h) | Assignment Midterm | CLO2 |
9 | Midterm | |||
10 | Supervised learning: Linear Regression, Logistic Regression – formulation, cost function | Lecture (3h) | Project Assignment | CLO2, 3 |
11 | Gradient vector, Gradient Descent: Batch, Mini-batch, Stochastic Gradient Descent, L2 regularization, hyper-parameter tuning | Lecture (3h) | Project Final Exam | CLO2, 3 |
12 | Neural Networks: MLP, Backpropagation, Multiclass classification: Softmax cost function, Training of Neural Networks | Lecture (3h) | Project Final Exam | CLO2, 3 |
Textbooks
- [CA] David Poole and Alan Mackworth, Artificial Intelligence: Foundations of Computational Agents, 3rd ed., Cambridge University Press, 2023. Available online at https://artint.info/
- [AIMA] Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 3rd edition, Prentice Hall, Inc. (2010)
Similar courses
- UBC
- UC Berkeley (lecture videos available on YouTube)
- JHU