Artificial Intelligence I: Meta-Heuristics and Games in Java
Learn powerful optimization techniques! Explore graph, genetic, and swarm intelligence algorithms. Master heuristics & meta-heuristics for problem-solving.
Course Content
Artificial Intelligence I: Meta-Heuristics and Games in Java is an all-levels Udemy course taught by Holczer Balazs. It runs 9h 8m, is taught in English, and includes a certificate of completion. Learners rate it 4.5 out of 5 from 842 reviews, with 8,556 students enrolled. It is a paid course, last updated March 2022.
Explore the Fundamentals of Artificial Intelligence
This course dives into the core concepts of artificial intelligence (AI), a rapidly evolving field transforming industries from software engineering to investment banking. Discover how learning algorithms are used to recognize patterns with applications ranging from cancer detection to predicting stock price movements.
Graph Algorithms for AI
- Breadth-First Search (BFS): Understand the principles of BFS and its importance in graph algorithms within AI. Learn why graph algorithms are fundamental to many AI applications.
- Depth-First Search (DFS): Master DFS, including its implementation using both iteration and recursion. Explore its use in applications like maze escape and visualize its stack memory behavior.
- Iterative Deepening Depth-First Search (IDDFS): Learn about IDDFS, a powerful technique for DFS with improved memory efficiency.
Optimization Techniques
- A Search Algorithm:* A comprehensive look at the A search algorithm*, a popular pathfinding method.
- Dijkstra's Algorithm vs. A:* Understand the key differences between Dijkstra's algorithm and A search*.
- Heuristics: Learn about heuristics and how they are used to guide search algorithms.
- Manhattan Distance & Euclidean Distance: Explore common distance metrics used in pathfinding.
- Optimization Approaches: Introduction to basic optimization algorithms, including brute-force search and hill climbing algorithm.
Meta-Heuristics for Complex Problems
- Simulated Annealing: Discover simulated annealing, a metaheuristic for finding the extremum of a function and solving combinatorial optimization problems.
- Traveling Salesman Problem (TSP): Apply simulated annealing to solve the classic traveling salesman problem (TSP).
- Genetic Algorithms: Explore genetic algorithms, inspired by artificial evolution and natural selection.
- Crossover & Mutations: Understand the core concepts of crossover and mutation in genetic algorithms.
- Knapsack Problem: Solve the knapsack problem using genetic algorithms.
- Particle Swarm Optimization (PSO): Learn about swarm intelligence and the Particle Swarm Optimization (PSO) algorithm.
Game Theory & AI
- Game Trees: Understand the concept of game trees and how to construct them.
- Minimax Algorithm & Game Engines: Explore the minimax algorithm and its application in game engines.
- Minimax Problem & Alpha-Beta Pruning: Address the limitations of game trees and learn how to improve efficiency with alpha-beta pruning.
- Chess Problem: Apply the minimax algorithm to solve a chess problem.
- Tic Tac Toe with Minimax: Implement the Tic Tac Toe game and apply the minimax algorithm for optimal play.
This course provides a strong foundation in essential AI techniques. We'll start with fundamental graph algorithms, then move to local search methods for optimization, and conclude with game theory applications. You'll gain practical experience by implementing a Tic Tac Toe game using the minimax algorithm.
Want AI in your product? Hire the team behind TutorialSearch.io
LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.