The world of artificial intelligence (AI) includes many areas in computing, which makes it a complex field. This course provides a useful description of AI, which will allow you to describe real-world problems as artificial environments.
Building intelligent agents (search, games, logic, constraint satisfaction problems)
Solving AI problems through programming with Python
Supervised learning techniques for regression and classification
Unsupervised learning techniques for data modeling and analysis
- Anyone interested in artificial intelligence and how it can be used to solve many problems.
What is Artificial Intelligence?
Field & Applications
Types of Agents
Number of Agents in Environment
Certainty in Environment
Defining Search Problems
Search Problems Examples
Representing Search Problems for Search Algorithms
Brute Force Searching
Constraint Satisfaction Problems
What Are Constraint Satisfaction Problems (CSPs)?
Using Inference with Search
Using a Local Search for CSPs
Solving a Sudoku Puzzle
Understanding Utility Theory
Markov Decision Process
Partially Observable Markov Decision Process (POMDP)
Learning for Computers
What Is Reinforcement Learning?
Additive and Discounted Rewards
Direct Utility Estimation
Temporal Difference Learning
Exploration and Exploitation Policies