Artificial Intelligence Notes by David Marshall

• Artificial Intelligence II - Introduction
  • AI Systems and Definitions
  • An example of intelligent action
  • Summary
    • Our way forward
  • Further reading
  • Exercise
• AI Key Concepts - Revisited
  • Problems and Search
    • Problem Definition
    • Searching
    • Heuristic Search
  • Knowledge Representation and Search
    • And-Or Graphs
    • AO* Algorithm
  • Means-Ends Analysis
  • Constraint Satisfaction
  • Why are these topics important?
  • Further reading
  • Exercises
• Knowledge Representation
  • What to Represent?
  • Using Knowledge
  • Properties for Knowledge Representation Systems
  • Approaches to Knowledge Representation
    • Simple relational knowledge
    • Inheritable knowledge
  • Inferential Knowledge
    • Procedural Knowledge
  • Issue in Knowledge Representation
  • Summary and the way forward
  • Further Reading
• Logic Knowledge Representation
  • Predicate logic
    • An example
    • Isa and instance relationships
  • Applications and extensions
  • Further reading
  • Exercises
• Procedural Knowledge Representations
  • Declarative or Procedural?
  • An Example
  • Representing How to Use Knowledge
  • Further reading
  • Exercises
• Weak Slot and Filler Structures
  • Why use this data structure?
  • Semantic Nets
    • Representation in a Semantic Net
    • Inference in a Semantic Net
    • Extending Semantic Nets
  • Frames
    • Frame Knowledge Representation
    • Interpreting frames
  • Further Reading
  • Exercises
• Strong Slot and Filler Structures
  • Conceptual Dependency (CD)
  • Scripts
  • CYC
  • Further Reading
  • Exercises
• Reasoning with Uncertainty: Non-Monotonic Reasoning
  • What is reasoning?
  • How can we reason?
  • Uncertain Reasoning?
  • Non-Monotonic Reasoning
    • Default reasoning
    • Circumscription
    • Implementations: Truth Maintenance Systems
  • Further Reading
  • Exercises
• Uncertain Reasoning: Statistical Methods
  • Symbolic versus statistical reasoning
  • Basic Statistical methods -- Probability
    • Bayes Theorem
  • Belief Models and Certainty Factors
    • Reasoning with Certainty factors
    • Overcoming the Bayes Rule shortcomings
  • Dempster-Shafer Models
    • Dempster-Shafer Calculus
    • Combining beliefs
  • Bayesian networks
    • Implementation
    • Reasoning in Bayesian nets
    • A Practical Example
  • Fuzzy Logic
    • Fuzzy Set Theory
  • Further Reading
  • Exercises
• Distributed Reasoning
  • Introduction
  • Distributed reasoning systems
  • Blackboard systems
    • Knowledge organisation and reasoning
    • Implementation issues
    • Problem solving and reasoning
    • Example Systems
  • Message Passing Systems
  • Further Reading
  • Exercises
• Planning I
  • What does planning involve?
  • Search in Planning
  • Blocks World Planning Examples
  • Planning System Components
    • Choice of best rule
    • Rule application
    • Detecting Progress
  • Goal Stack Planning
    • Sussman Anomaly (1975)
  • Further Reading
  • Exercises
• Planning II
  • Nonlinear Planning Using Constraint Posting
    • Tweak Heuristics Using Constraint Posting
  • Further Reading
  • Exercises
• Learning I
  • What is Learning?
    • How can we learn?
  • Rote Learning
    • Store v Compute
  • Learning by Taking Advice
    • Automated Advice Taking
    • Knowledge Base Maintenance
    • Example Learning System - FOO
  • Learning by Problem Solving
    • Learning by Parameter Adjustment
    • Learning by Macro Operators
    • Learning by Chunking
• Learning II
  • Inductive Learning
    • A Blocks World Learning Example -- Winston (1975)
    • Version Spaces
    • Decision Trees
  • Explanation Based Learning (EBL)
    • EBL example
  • Discovery
    • Theory Driven Discovery - AM (1976)
    • Data Driven Discovery -- BACON (1981)
  • Analogy
    • Transformational Analogy
    • Derivational Analogy
  • Further Reading
  • Exercises
• Common Sense
  • The Physical World -- Qualitative Physics
    • Modelling the Qualitative World
    • Reasoning with qualitative information
  • Common sense Ontologies
    • Time
    • Space
    • Materials
  • Memory Organisation
  • Memory in problem solving
  • Further Reading
  • Exercises
• Vision I
  • The Challenge of Vision
  • Image Acquisition
    • 2D Image Input
    • 3D imaging
  • Geometric Modelling for Computer Vision
    • Wireframe Models
    • Set-Theoretic Modelling
    • Boundary Representation
    • Desirable Model Properties for Vision
  • Further Reading
  • Exercises
• Vision II
  • Line Labelling
    • Introduction
    • Assumptions
    • Junction Types
    • Labelling an Image
  • Relaxation Labelling
    • Statistical Relaxation Techniques
  • Further Reading
  • Exercises
• VISION III
  • Object Recognition
    • Invariants
    • Pattern Recognition
    • Hough Transforms
    • Extended Gaussian Images
  • Further Reading
  • Exercises
• Vision IV
  • Model Based Object Recognition
    • Tree Search Methods
    • Some Matching Case Studies
    • Relaxation Labelling Methods
    • Graph Searching
  • Further Reading
  • Exercises
• About this document ...