Final Examination
CSE 415: Introduction to Artificial Intelligence
The University of Washington, Seattle, Autumn 2009
Date: Wednesday, December 16 (2:30-4:30PM)
Format: The final exam will be similar in format to the midterm exam. The topics covered will be drawn from the following, which includes some topics from the first part of the course and some from the second.
Topics:
The Turing Test

Python Data Structures
  Dictionaries (hashes):
   creating, accessing, iterating over
  Lists: 
   creating, accessing (including slices), copying,
   deep vs shallow copying

State-space search
  states, state spaces, operators, preconditions, moves,
  heuristic evaluation functions,
  iterative depth-first search, recursive depth-first search,
  breadth-first search, best-first search, uniform-cost search,
  iterative deepening, A* search.

Minimax search for 2-player, zero-sum games
  Static evaluation functions
  Backed up values
  Alpha-beta pruning
  Zobrist hashing

Predicate logic
  Interpretations, satisfiability, consistency, models
  Resolution
  Horn clauses
  PROLOG syntax

Probabilistic reasoning
  Bayes' rule
  Odds and conversion between odds and probability
  Bayes nets

Image understanding
  Human vision: subjective contour illusion, pareidolia
  Shannon sampling
  Quantization
  Histograms
  Thresholding
  Valley method for threshold selection
  Hough transform
    polar coordinates representation of lines
    hit functions for circles and ellipses
    parameter space array
    voting process
    peak detection
  Edge Detection with the Roberts Cross Operator
  Four-connectedness, eight-connectedness of sets of pixels
  Formal Segmentation into Regions
  Morphology transformations
    erosion
    dilation
  Scene analysis with Guzman's labelling method

Perceptrons
  How to compute AND, OR, and NOT.
  Simple pattern recognition (e.g., 5 x 5 binary image
    inputs for optical character recognition)
  Training sets, training sequences, and the perceptron 
    training algorithm.
  Linear separability and the perceptron training theorem.

Natural Language Understanding
  Grammars, nonterminals, terminals, productions
  Sentential forms, derivations, the language specified by a grammar
  Case frames
  Controlled language, semantic grammar

Robotics
  Asimov's Three Laws of Robotics

The Future of AI
  Kurzweil's "singularity"

Sample problems: Here are sample multiple-choice problems for 2nd-half-of-the-quarter topics. Click here for solutions.