1. AI Concepts

definitions of AI: intelligent in human, humans better at, symbolic,
    heuristic, pattern matching, learning, the Turing test
why it is hard to define; the two fallacies
areas: robotics, vision, human language, expert systems,
theorem proving, games, problem solving, machine learning
 

2. LISP

functional/applicative programming (versus procedural/imperative)
function evaluation (application), quote, math functions
atoms, lists, S-expressions; null list; car, cdr, cons, list;
predicates: Boolean values (t, nil), atom, null, equality
functions; defun, lambda, cond; recursion; symbols, setq;
special forms (cond, lambda); conditionals: cond, and, or
iteration: (recursion preferred), dolist, dotimes, do
applicative and mapping: apply, funcall, mapcar, maplist
I/O: read, read-line, print, princ, terpri
property lists & association lists; using specific LISP dialect
writing simple and star recursive functions (numbers & lists)
 

3. Logic methods

propositional & predicate calculus; laws/derivation rules
converting to clause form
resolution: matching (unification) of clauses,
using resolution for proofs
 

4. State space search methods

state space, state variables, operators/move generators,
forward (data-driven) & backward (goal-driven),
trees and graphs, search space, search strategies
weak search methods: generate & test, depth/breadth first,
    branching factors, combinatorial explosion
heuristic methods: best vs. first solution, hill climb, best-first;
admissibility, monotonicity, informedness
zero-sum games, minimax move evaluation, alpha-beta pruning
 

5. Expert systems

history; limited domain; knowledge engineering; development;
shell structure: knowledge base (rules+data), inference engine,
user interface, explanation facility, knowledge update
Knowledge Engineering, process, scoping domain, selecting expert
tools: levels
 

6. Knowledge representation

knowledge representation principles: representational
adequacy, acquisitional efficiency, inferential adequacy,
    inferential efficiency
predicate logic, OAV, conceptual graphs & semantic nets,
    conceptual dependency, frames, scripts
non-monotonic logic issues
reasoning under uncertainty: Bayesian, Dempster-Shafer, Stanford
relative measures and fuzzy logic/sets
 

7. Natural language processing

natural vs. formal language; spoken language
written language: character-recognition, linguistic levels
    (syntactic, semantic, pragmatic), formal grammar components & CFG,
meta-language, parsing, ambiguity, resolving ambiguity
processing vs."understanding", TNs, RTNs, ATNs;
implementing RTNs and ATNs with recursive functions;
stochastic (Markov model) and clustering approaches to language;
language application systems
 

8. Machine learning basics

definition of learning
aproaches to learning: symbolic, connectionist, evolutionist
inductive bias concepts, theory of learnability
decision tree concept representation (ID3), Shannon's formula
 

9. Neural Networks

neuron physiology: parts(soma, dendrites, axon, synapse),
behavior(activation, inputs, output firing), connectivity
modeling/simplification: net input (linear superposition),
    weight matrix, smoothed output, simple network models
    (forward feed, pools), activation functions/dynamic calculation
simple learning models: Perceptrons, Hebb rule, Delta rule;
forced patterns, training epochs & order; Perceptron weaknesses
multi-layer learning: Back Propagation, derivation (minimize
    mean-square error, partial derivatives), logistic activation
    function, pattern learning process (apply inputs, forward
    calculate, output error deltas, back-propagation, adjustments)
competitive/Kohonen learning: multi-layer, clusters, discrete activ,
    no training output, normalized weights & learning rule
    (only for most active unit, proportionate decrement, increment on)
 

10. Genetic Algorithms

applicability: efficient search, adaptability, relative goodness
basic model: encoded parameter set, population of points,
    goodness function interpreted as survival probability,
method: reproduction, crossover, mutation; generations, evolution
    of population; implementation of reproduction, crossover, mutation
classifier learning model: receptor, message list, effector,
    productions, auction economy, evolution of classifier population