| Communicating, perceiving and acting |
| Probabilistic Language Processing |
| Solving Problems by Searching |
| Informed Search and Exploration |
| Constraint Satisfaction Problems |
| Inference in First-Order Logic |
| Planning and Acting in the Real World |
| Uncertain knowledge and reasoning |
| Probabilistic Reasoning over Time |
| Learning from Observations |
| Statistical Learning Methods |
| Artificial Intelligence: A Modern Approach |
| by Stuart Russell and Peter Norvig |
| Artificial Intelligence: Conclusions |
| Philosophical Foundations |
| Weak AI: Can Machines Act Intelligently? |
| The argument from disability |
| The mathematical objection |
| The argument from informality |
| Strong AI: Can Machines Really Think? |
| The "brain in a vat"' experiment |
| The brain prosthesis experiment |
| The Ethics and Risks of Developing Artificial Intelligence |
| Are We Going in the Right Direction? |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Mathematical background Artificial Approach |
| Complexity Analysis and O() Notation |
| NP and inherently hard problems |
| Probability Distributions |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Introduction in Artificial Intelligence |
| The cognitive modeling approach |
| The "laws of thought'' approach |
| >>Note: Thinking rationally |
| The rational agent approach |
| >>Note: Acting rationally |
| The History of Artificial Intelligence |
| The Foundations of Artificial Intelligence |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| The History of Artificial Intelligence |
| The gestation of artificial intelligence (1943-1955) |
| The birth of artificial intelligence (1956) |
| Early enthusiasm, great expectations (1952-1969) |
| A dose of reality (1966-1973) |
| Knowledge-based systems: The key to power? (1969-1979) |
| AI becomes an industry (1980-present) |
| The return of neural networks (1986-present) |
| AI becomes a science (1987-present) |
| The emergence of intelligent agents (1995-present) |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| The Foundations of Artificial Intelligence |
| Philosophy (428 B.C.-present) |
| Mathematics (B.C. 800-present) |
| Neuroscience (1861-present) |
| Psychology (1879-present) |
| Computer engineering (1940-present) |
| Control theory and Cybernetics (1948-present) |
| Linguistics (1957-present) |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Model-based reflex agents |
| Good Behavior: The Concept of Rationality |
| Omniscience, learning, and autonomy |
| The Nature of Environments |
| Specifying the task environment |
| Properties of task environments |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Solving Problems by Searching |
| Well-defined problems and solutions |
| Measuring problem-solving performance |
| Uninformed Search Strategies |
| Iterative deepening depth-first search |
| Comparing uninformed search strategies |
| Searching with Partial Information |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Informed Search and Exploration |
| Informed (Heuristic) Search Strategies |
| A* search: Minimizing the total estimated solution cost |
| Memory-bounded heuristic search |
| Learning to search better |
| The effect of heuristic accuracy on performance |
| Inventing admissible heuristic functions |
| Learning heuristics from experience |
| Local Search Algorithms and Optimization Problems |
| Simulated annealing search |
| Local Search in Continuous Spaces |
| Online Search Agents and Unknown Environments |
| Learning in online search |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Constraint Satisfaction Problems |
| Constraint Satisfaction Problems |
| Backtracking Search for CSPs |
| Variable and value ordering |
| Propagating information through constraints |
| Handling special constraints |
| Intelligent backtracking: looking backward |
| Local Search for Constraint Satisfaction Problems |
| The Structure of Problems |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Optimal Decisions in Games |
| Optimal decisions in multiplayer games |
| Imperfect, Real-Time Decisions |
| Games That Include an Element of Chance |
| Position evaluation in games with chance nodes |
| Complexity of expectiminimax |
| State-of-the-Art Game Programs |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Reasoning Patterns in Propositional Logic |
| Completeness of resolution |
| Forward and backward chaining |
| >>Note: A Very Simple Logic |
| Agents Based on Propositional Logic |
| Finding pits and wumpuses using logical inference |
| Keeping track of location and orientation |
| Effective propositional inference |
| A complete backtracking algorithm |
| Hard satisfiability problems |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Syntax and Semantics of First-Order Logic |
| Existential quantification |
| Connections between Forall and Exists |
| Models for first-order logic |
| Symbols and interpretations |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Knowledge Engineering in First-Order Logic |
| The knowledge engineering process |
| The electronic circuits domain |
| Assemble the relevant knowledge |
| Encode general knowledge of the domain |
| Encode the specific problem instance |
| Pose queries to the inference procedure |
| Assertions and queries in first-order logic |
| Syntax and Semantics of First-Order Logic |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Inference in First-Order Logic |
| A backward chaining algorithm |
| Efficient implementation of logic programs |
| Redundant inference and infinite loops |
| Constraint logic programming |
| Propositional vs. First-Order Inference |
| Inference rules for quantifiers |
| Reduction to propositional inference |
| A first-order inference rule |
| First-order definite clauses |
| A simple forward-chaining algorithm |
| Efficient forward chaining |
| Matching rules against known facts |
| Incremental forward chaining |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Inference in First-Order Logic |
| Conjunctive normal form for first-order logic |
| The resolution inference rule |
| Completeness of resolution |
| Design of a theorem prover |
| Theorem provers as assistants |
| Practical uses of theorem provers |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Actions, Situations and Events |
| The ontology of situation calculus |
| Describing actions in situation calculus |
| Solving the representational frame problem |
| Solving the inferential frame problem |
| Truth Maintenance Systems |
| Mental Events and Mental Objects |
| A formal theory of beliefs |
| Knowledge, time, and action |
| Reasoning Systems for Categories |
| Reasoning with Default Information |
| Negation as failure and stable model semantics |
| Circumscription and default logic |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Rational AI Agents: Planning |
| Planning with State-Space Search |
| Forward state-space search |
| Backward state-space search |
| Heuristics for state-space search |
| The language of planning problems |
| A partial-order planning example |
| Partial-order planning with unbound variables |
| Heuristics for partial-order planning |
| Analysis of Planning Approaches |
| Planning graphs for heuristic estimation |
| Planning with Propositional Logic |
| Describing planning problems in propositional logic |
| Complexity of propositional encodings |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Planning and Acting in the Real World |
| Cooperation: Joint goals and plans |
| Time, Schedules, and Resources |
| Scheduling with resource constraints |
| Hierarchical Task Network Planning |
| Representing action decompositions |
| Modifying the planner for decompositions |
| Conditional planning in fully observable environments |
| Conditional planning in partially observable environments |
| Planning and Acting in Nondeterministic Domains |
| Execution Monitoring and Replanning |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Communicating, perceiving and acting |
| Language generation with DCGs |
| The structure of coherent discourse |
| The component steps of communication |
| A Formal Grammar for a Fragment of English |
| Generative capacity of augmented grammars |
| Syntactic Analysis (Parsing) |
| Ambiguity and Disambiguation |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Communicating, perceiving and acting |
| Probabilistic Language Processing |
| Probabilistic Language Models |
| Probabilistic context-free grammars |
| Learning probabilities for PCFGs |
| Learning rule structure for PCFGs |
| Presentation of result sets |
| Machine translation systems |
| Statistical machine translation |
| Learning probabilities for machine translation |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Communicating, perceiving and acting |
| Images without lenses: the pinhole camera |
| Light: the photometry of image formation |
| Color: the spectrophotometry of image formation |
| Early Image Processing Operations |
| Extracting Three-Dimensional Information |
| Brightness-based recognition |
| Feature-based recognition |
| Using Vision for Manipulation and Navigation |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Communicating, perceiving and acting |
| Cell decomposition methods |
| Robotic Software Architectures |
| Robotic programming languages |
| Planning uncertain movements |
| Other types of perception |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Learning from Observations |
| Decision trees as performance elements |
| Expressiveness of decision trees |
| Inducing decision trees from examples |
| Assessing the performance of the learning algorithm |
| Broadening the applicability of decision trees |
| Computational Learning Theory |
| >>Note: Why Learning Works |
| How many examples are needed? |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| A Logical Formulation of Learning |
| Current-best-hypothesis search |
| Explanation-Based Learning |
| Extracting general rules from examples |
| Learning Using Relevance Information |
| Determining the hypothesis space |
| Learning and using relevance information |
| Inductive Logic Programming |
| Top-down inductive learning methods |
| Inductive learning with inverse deduction |
| Making discoveries with inductive logic programming |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Statistical Learning Methods |
| Learning with Complete Data |
| Maximum-likelihood parameter learning: Discrete models |
| Maximum-likelihood parameter learning: Continuous models |
| Bayesian parameter learning |
| Learning Bayes net structures |
| Learning with Hidden Variables: The EM Algorithm |
| Unsupervised clustering: Learning mixtures of Gaussians |
| Learning Bayesian networks with hidden variables |
| Learning hidden Markov models |
| The general form of the EM algorithm |
| Learning Bayes net structures with hidden variables |
| Single layer feed-forward neural networks (perceptrons) |
| Multilayer feed-forward neural networks |
| Learning neural network structures |
| Case Study: Handwritten Digit Recognition |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Passive Reinforcement Learning |
| Direct utility estimation |
| Adaptive dynamic programming |
| Temporal difference learning |
| Active Reinforcement Learning |
| Learning an Action-Value Function |
| Generalization in Reinforcement Learning |
| Applications to game-playing |
| Application to robot control |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Uncertain knowledge and reasoning |
| Handling uncertain knowledge |
| Uncertainty and rational decisions |
| Design for a decision-theoretic agent |
| Basic Probability Notation |
| The Axioms of Probability |
| Using the axioms of probability |
| Why the axioms of probability are reasonable |
| Inference Using Full Joint Distributions |
| Applying Bayes' rule: The simple case |
| Using Bayes' rule: Combining evidence |
| The Wumpus World Revisited |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Uncertain knowledge and reasoning |
| Representing Knowledge in an Uncertain Domain |
| The Semantics of Bayesian Networks |
| Representing the full joint distribution |
| A method for constructing Bayesian networks |
| Compactness and node ordering |
| Conditional independence relations in Bayesian networks |
| Efficient Representation of Conditional Distributions |
| Bayesian nets with continuous variables |
| Exact Inference in Bayesian Networks |
| The variable elimination algorithm |
| The complexity of exact inference |
| Approximate Inference in Bayesian Networks |
| Rejection sampling in Bayesian networks |
| Inference by Markov chain simulation |
| Extending Probability to First-Order Representations |
| Other Approaches to Uncertain Reasoning |
| Rule-based methods for uncertain reasoning |
| Representing ignorance: Dempster-Shafer theory |
| Representing vagueness: Fuzzy sets and fuzzy logic |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Uncertain knowledge and reasoning |
| Probabilistic Reasoning over Time |
| Stationary processes and the Markov assumption |
| Inference in Temporal Models |
| Finding the most likely sequence |
| Simplified matrix algorithms |
| Updating Gaussian distributions |
| A simple one-dimensional example |
| Applicability of Kalman filtering |
| Dynamic Bayesian Networks |
| Approximate inference in DBNs |
| Building a speech recognizer |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Uncertain knowledge and reasoning |
| Combining Beliefs and Desires under Uncertainty |
| The Basis of Utility Theory |
| Constraints on rational preferences |
| And then there was Utility |
| Utility scales and utility assessment |
| Multiattribute Utility Functions |
| Preference structure and multiattribute utility |
| Preferences without uncertainty |
| Preferences with uncertainty |
| Representing a decision problem with a decision network |
| Evaluating decision networks |
| Properties of the value of information |
| Implementing an information-gathering agent |
| Decision-Theoretic Expert Systems |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| Uncertain knowledge and reasoning |
| The value iteration algorithm |
| Convergence of value iteration |
| Partially observable MDPs |
| Decision-Theoretic Agents |
| Decisions with Multiple Agents: Game Theory |
| Sequential Decision Problems |
| Optimality in sequential decision problems |
| Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig |
| |