Artificial Intelligence
This study material is a complete free handbook of Artificial Intelligence with diagrams and graphs. It is part of Computer science or software engineering education which brings important topics, notes, news & blog on the subject. This study material serves as a quick reference guide on this engineering subject.
Each topic is complete with diagrams, equations and other forms of graphical representations for better learning and quick understanding. This study material will provide faster learning and quick revisions on the subject.
Introduction to AI
Problem solving with AI
Knowledge and Reasoning
Learning
Natural Language Processing
- Turing test
- Introduction to Artificial Intelligence
- History of AI
- The AI Cycle
- Knowledge Representation
- Typical AI problems
- Limits of AI
- Introduction to Agents
- Agent Performance
- Intelligent Agents
- Structure Of Intelligent Agents
- Types of agent program
- Goal based Agents
- Utility-based agents
- Agents and environments
- Agent architectures
- Search for Solutions
- State Spaces
- Graph Searching
- A Generic Searching Algorithm
- Uninformed Search Strategies
- Breadth-First Search
- Heuristic Search
- A∗ Search
- Search Tree
- Depth first Search
- Properties of Depth First Search
- Bi-directional search
- Search Graphs
- Informed Search Strategies
- Methods of Informed Search
- Greedy Search
- Proof of Admissibility of A*
- Properties of Heuristics
- Iterative-Deepening A*
- Other Memory limited heuristic search
- N-Queens eample
- Adversarial Search
- Genetic Algorithms
- Games
- Optimal decisions in Games
- minimax algorithm
- Alpha Beta Pruning
- Backtracking
- Consistency Driven Techniques
- Path Consistency (K-Consistency)
- Look Ahead
- Propositional Logic
- Syntax of Propositional Calculus
- Knowledge Representation and Reasoning
- Propositional Logic Inference
- Propositional Definite Clauses
- Knowledge-Level Debugging
- Rules of Inference
- Soundness and Completeness
- First Order Logic
- Unification
- Semantics
- Herbrand Universe
- Soundness, Completeness, Consistency, Satisfiability
- Resolution
- Herbrand Revisited
- Proof as Search
- Some Proof Strategies
- Non-Monotonic Reasoning
- Truth Maintenance Systems
- Rule Based Systems
- Pure Prolog
- Forward chaining
- backward Chaining
- Choice between forward and backward chaining
- AND/OR Trees
- Hidden Markov Model
- Bayesian networks
- Learning Issues
- Supervised Learning
- Decision Trees
- Knowledge Representation Formalisms
- Semantic Networks
- Inference in a Semantic Net
- Extending Semantic Nets
- Frames
- Slots as Objects
- Interpreting frames
- Introduction to Planning
- Problem Solving vs. Planning
- Logic Based Planning
- Planning Systems
- Planning as Search
- Situation-Space Planning Algorithms
- Partial-Order Planning
- Plan-Space Planning Algorithms
- Interleaving vs. Non-Interleaving of Sub-Plan Steps
- Simple Sock/Shoe Example
- Probabilistic Reasoning
- Review of Probability Theory
- Introduction to Learning
- Taxonomy of Learning Systems
- Mathematical formulation of the inductive learning problem
- Concept Learning
- Concept Learning as Search
- Algorithm to Find a Maximally-Specific Hypothesis
- Candidate Elimination Algorithm
- The Candidate-Elimination Algorithm
- Decision Tree Construction
- Splitting Functions
- Decision Tree Pruning
- Neural Networks
- Artificial Neural Networks
- Perceptron
- Perceptron Learning
- Multi-Layer Perceptrons
- Back-Propagation Algorithm
- Statistical learning
- Learning With Complete Data
- Naive Bayes models
- Maximum-likelihood parameter learning: Continuous models
- Bayesian parameter learning
- Learning Bayes net structures
- Learning With Hidden Variables
- Unsupervised clustering: Learning mixtures of Gaussians
- Learning Bayesian networks with hidden variables
- Learning hidden Markov models
- The general form of the EM algorithm
- Reinforcement learning
- Passive Reinforcement Learning
- Natural Language Processing
- Ambiguity
- Natural Language Understanding
- Natural Language Generation
- Steps in Language Understanding and Generation
- Introduction to Pattern Recognition
- Pattern Recognition Methodologies
- Pattern Recognition Algorithms
- Statistical algorithms
- Clustering Algorithms
- Regression Algorithms
- Sequence Labeling Algorithms
- Usage & Application pattern Recognition