This is a repository of projects and exercies performed while going through the Udacity Artificial Intelligence Nanodegree. Below are lists of the following projects to be built and completed during the course:
- Build a Sudoku Solver
- Build a Forward Planning Agent
- Build an Adversarial Game Playing Agent
- Part of Speech Tagging
- Constraint Satisfaction Problems
- Local Search
The following are descriptions for each product as outlined in the nanodegree syllabus Humans use reason to solve problems by decomposing the problem statement and incorporating domain knowledge to limit the possible solution space. In this project, I use a technique called constraint propagation together with backtracking search to make an agent that only considers reasonable solution candidates and efficiently solves any Sudoku puzzle. This approach appears in many classical AI problems, and the solution techniques have been extended and applied to diverse problems in bioinformatics, logistics, and operations research. In this project I demonstrate some basic algorithms knowledge, and use of constraint satisfaction to solve general problems Intelligent agents are expected to act in complex domains where their goals and objectives may not be immediately achievable. They must reason about their goals and make rational choices of actions to achieve them. In this project I build a system using symbolic logic to represent general problem domains and use classical search to find optimal plans for achieving my agent’s goals. Planning & scheduling systems power modern automation & logistics operations, and aerospace applications like the Hubble telescope & NASA Mars rovers. In this project I demonstrate an understanding of classical optimization & search algorithms, symbolic logic, and domain-independent planning. AI agents acting in the real world have to “hope for the best, but prepare for the worst.” In this project, I write an agent that uses that idea to make rational choices to achieve super-human performance in games competing against adversarial agents. The principles of adversarial search provide a foundation for autonomous agents acting in the real world, and for understanding modern advances in AI like DeepMind’s AlphaGo Zero. In this project I demonstrate advanced algorithms knowledge, including minimax with alpha-beta pruning for adversarial search. Probabilistic models allow my agents to better handle the uncertainty of the real world by explicitly modeling their belief state as a distribution over all possible states. In this project I use a Hidden Markov Model (HMM) to perform part of speech tagging, a common pre-processing step in Natural Language Processing. HMMs have been used extensively in NLP, speech recognition, bioinformatics, and computer vision tasks.