Computational AI & Intelligent Agents with Python
Engineering autonomous computational agents: hierarchical control, CSP arc consistency, probabilistic Bayesian networks, MDPs, and deep Q-learning.
Course Overview
Step into rigorous computational artificial intelligence. Design autonomous agents operating in complex environments through perception-action loops, implement arc consistency (AC-3) for constraint satisfaction, construct top-down Horn clause inference engines, train neural perceptrons, compute belief updates in Bayesian probability networks, and master reinforcement learning via Markov Decision Processes and Q-learning.
What You'll Learn & Build
Prerequisites
- Solid Python proficiency (classes, OOP, recursion, dictionary mappings)
- Basic calculus (derivatives for gradient descent) and basic probability theory
Who This Is For
- Advanced software engineers, robotics developers, autonomous systems researchers, and graduate students
Course Curriculum & Lessons
4 Modules • 12 Total Lessons • Lessons 1-4 are Free to Solve-
1. Intelligent Agent Architectures & Perception Loops
-
2. Generic Graph Search with Priority Queues
-
3. Branch-and-Bound Search with Bound Pruning
-
4. Constraint Satisfaction Problems & The AC-3 Algorithm
-
5. Backtracking Search with MRV & Forward Checking
-
6. Propositional Definite Clauses & Top-Down Proofs
-
7. The Perceptron Algorithm & Decision Boundaries
-
8. Multi-Layer Networks & Gradient Backpropagation
-
9. Continuous Feature Splitting in Decision Trees
-
10. Reasoning Under Uncertainty: Bayes Theorem in Python
-
11. Bayesian Belief Networks & Variable Elimination
-
12. Reinforcement Learning: Bellman Updates & Q-Learning
Your Instructor
Autonomous Agents & Robotics Lab
Senior software architect with extensive production engineering experience. Builds clean, modern curriculum and interactive web playgrounds for developers.
