This repository contains the implementation of fundamental concepts in Artificial Intelligence, covering topics such as search algorithms, probabilistic reasoning, neural networks, and reinforcement learning. Each module focuses on key AI techniques and algorithms, with examples and code to explore these concepts.
- Module 1: Introduction to AI and Search
- Module 2: Probabilistic Reasoning
- Module 3: Neural Networks
- Module 4: Reinforcement Learning and Computational Game Theory
- How to Run
This module covers various search techniques used in AI, focusing on solving configuration and planning problems through:
- Breadth-first search (BFS)
- Uniform cost search
- Depth-first search (DFS)
- Iterative deepening search
- Bi-directional search
- Heuristic search techniques
- Adversarial search & Alpha-beta pruning
Learn about reasoning under uncertainty, with a focus on:
- Bayes' theorem and its applications
- Bayesian networks (Graphical Models)
- Markov Networks and Hidden Markov Models (HMM)
- Decision Trees and Random Forests
Explore the structure and behavior of neural networks, including:
- Neuron as a nonlinear combiner
- Feed-forward networks and the Universal Approximation Theorem
- Hopfield Network and Associative Memory
Dive into decision-making processes and game theory through:
- Markov Decision Processes (MDPs)
- Reinforcement Learning (Q-learning, SARSA)
- Extensive form games
- Social Choice Theory and Mechanism Design
-
Clone this repository:
git clone https://github.com/your-username/ai-fundamentals.git cd ai-fundamentals -
Install the requires dependencies
pip install -r requirements.txt
-
Run individual modules to explore different AI techniques. For example, to run the search algorithms:
python search_algorithms.py