Artificial Intelligence

• Game Playing
  • Overview
  • Isolation Game
    • Building a Game Tree
  • Minimax Algorithm
    • Complexity
    • Depth-Limited Search
  • Evaluation Functions
    • Quiescent Search
    • Horizon Effect
  • Iterative Deepening
  • Alpha-Beta Pruning
  • Multi-Player Games
    • 3-Player Games
    • Multi-Player Alpha-Beta Pruning
    • Probabilistic Games
  • Further Reading
• Search
  • Problem Solving
    • Problem Definition
  • Tree Search
    • Graph Search
  • Uninformed Search Strategies
    • Breadth-First Search (BFS)
    • Depth-First Search (DFS)
    • Uniform Cost Search (UCS)
    • Search Strategy Comparison
  • Informed (Heuristic) Search
    • Greedy Best-First Search
    • A* Search
    • Admissible Heuristic
    • Consistent (Monotone) Heuristic
  • State Spaces
  • Sliding Blocks Puzzle
  • Tri-Directional Search
  • Rubik’s Cube Search
  • Problems with Search
  • References
• Pre-processing for Search
  • Resources explaining Landmarks, Reach, and Shortcuts
  • Google Maps Transfer Patterns
• Constraint Satisfaction
  • CSP Fundamentals
    • Definition
    • Map Coloring Example
  • Backtracking Search
    • Basic Algorithm
    • Variable Ordering — MRV
    • Value Ordering — LCV
    • Forward Checking
  • Constraint Propagation and Arc Consistency
    • Arc Consistency (AC-3)
  • Structured CSPs
  • Iterative (Local Search) Methods
• Simulated Annealing
  • Optimization and Local Search
    • Traveling Salesman Problem
    • N-Queens Problem
  • Hill Climbing
    • Local Maxima and Plateaus
    • Step Size
    • Random Restarts
  • Simulated Annealing Algorithm
    • Annealing Intuition
    • Algorithm
    • Temperature Schedule
  • Local Beam Search
  • Genetic Algorithms
    • Representation
    • Fitness and Selection
    • Crossover
    • Mutation
    • GA Summary
• Probability
  • Fundamentals
    • Independence
    • Total Probability
  • Bayes Rule
    • Conditional Probability Example
    • Cancer Test Example
  • Bayes Networks Overview
• Reference
• Bayes Nets
  • Structure and Parameters
    • Computing Bayes Rule
    • Two-Test Cancer Example
  • Conditional Independence
    • Absolute vs. Conditional Independence
    • Confounding Cause
    • Explaining Away
  • D-Separation
  • Probabilistic Inference
    • Enumeration
    • Variable Elimination
  • Approximate Inference — Sampling
    • Direct Sampling
    • Rejection Sampling
    • Likelihood Weighting
    • Gibbs Sampling
• Machine Learning
  • Supervised Learning
    • k-Nearest Neighbors (k-NN)
    • Cross-Validation
    • Gaussian Distribution and Bayes Classification
    • Using Mixture of Gaussians
  • Decision Trees
    • Basics
    • Entropy and Information Gain
    • Minimum Description Length
    • Random Forests
  • Boosting
  • Neural Networks
    • Perceptron
    • Multilayer Networks
    • Back-Propagation
    • Deep Learning
  • Unsupervised Learning
    • k-Means Clustering
    • Expectation Maximization (EM)
    • Gaussian Mixture Models (GMM)
  • Resources
• Challenge: Expectimax Pruning
  • Pruning Rules
• Search Questions
• Challenge: Rubik’s Cube Heuristic
  • Cube Properties
  • Heuristic: 3D Manhattan Distance
• Challenge: Simulated Annealing & CSP
  • Simulated Annealing Calculations
  • CSP: Sudoku-like Grid
  • CSP: Menu Selection
• Challenge: Bayes Net Calculation
  • Problem 1: P(LD=T | Cough=T)
  • Problem 2: P(LD=T | Cough=T, Fever=T)
  • References
• Numpy References
  • numpy arrays
  • sum of log probabilities
• Logic and Planning
  • Propositional Logic
    • Truth Tables
    • Terminology
    • Limitations of Propositional Logic
  • First-Order Logic
    • Syntax
    • Models in FOL
    • Vacuum World Example
    • Higher-Order Logic
    • Unification and Resolution
  • Planning
    • Problem Solving vs. Planning
    • Planning vs. Execution
    • Belief State and Predict-Update Cycle
  • Classical Planning
    • STRIPS Representation
    • Search Strategies
    • Heuristics for Planning
  • Situation Calculus
• Planning Under Uncertainty
  • Markov Decision Processes
    • Core Concepts
    • MDP Grid World
    • Problems with Conventional Planning
    • Policy and Costs
    • Value Iteration
    • Policy Iteration
    • MDP Summary
  • Partially Observable MDPs
    • Overview
    • POMDP vs. MDP
    • POMDP Definition
    • Solving POMDPs
    • Reinforcement Learning Connection
    • Further Study
• Pattern Recognition Through Time
  • Overview
  • Hidden Markov Models
    • Definition
    • Three Fundamental Problems
  • Dynamic Time Warping
    • HMMs vs. DTW