00 Contents Flashcards
1
Q
Contents: Intelligent agents
A
Rational agent Tasks and evnironment - PEAS - Properties of environments Types of agents
2
Q
Contents: Searching
A
Formulation of a search problem Problem-solving agents Tree search vs. graph search Uninformed search strategies Evaluation of search strategies Informed search
3
Q
Contents: Logical agents
A
Knowledge-based agents Knowledge representation (languages) Logical reasoning - Entailment - Inference Propositional logic - Equivalence, validity and satisfiability - Inference by applying rules - Searching (forward and backward chaining) - Keeping track of state of the world
4
Q
Contents: First-order Logic (FOL)
A
Logical commitments Syntax First-order inference Generalized modus ponens Completeness Forward chaining Backward chaining Resolution
5
Q
Contents: Knowledge Engineering in FOL
A
Knowledge engineering vs. programming
Declarative approach
Knowledge engineering process (FOL)
6
Q
Contents: Knowledge Representation
A
General ontology
Elements of a general ontology
Description Logic
Default and non-monotonic logic
7
Q
Contents: Classical Planning
A
What is planning? Plan representation - Factored plan representation - How are planning actions applied? - Planning solution - Current popular planning approaches State-space search - Forward and backward state-space search - Heuristics for planningPlanning graphs - GRAPHPLAN Partial-order planning - Partial-order planning in plan space - Partial-order plan representation - POP
8
Q
Contents: Planning and acting
A
Planning and scheduling - With and without resource constraints Hierarchical task networks Planning in nondeterministic domains Continuous planning Multi-agent planning
9
Q
Contents: Quantifying Uncertainty
A
Agents and uncertainty
10
Q
Contents: Probabilistic Reasoning
A
Status of probability sentences Probability, utility and decisions Bayes' rule Bayesian networks Bayesian inference Other approaches to uncertainty
11
Q
Contents: Making Simple Decisions
A
Uncertainty and utility Maximum expected utility Preference structures Decision networks Value of information Decision analysis vs. expert systems Decision-theoretic expert systems
12
Q
Contents: Learning from examples
A
General model Types of learning Learning decision trees Neural networks - Basic unit - Activation functions - Neural network structures - Feed-forward networks as functions - Perceptrons - Multi-layer feed-forward networks - Learning neural network structure
13
Q
Contents: Reinforcement Learning
A
Sequential decision processes Markov Decision Processes Optimal policy and utility of states Bellman equations - Value iteration - Policy iteration Reinforcement learning of MDP Passive learning - Direct utility estimation - Adaptive Dynamic Programming (ADP) - Temporal Difference (TD) learning Active learning RL Applications
14
Q
Contents: Natural Language Communication
A
Communication and action Natural and formal languages Language structures Parsing - Top-down vs. bottom-up parsing Augmented grammar for semantics Steps of communication Machine translation
15
Q
Contents: Foundations and prospects
A
The big questions Weak vs. Strong AI The Turing test Objections to intelligent machines Strong AI - Machine consciousness Tentative answers to some big questions State-of-the-art Status of AI
