Requirements Midterm Exam
                    Graduate AI (Fall 2001)

The exam is open-books you can bring everything including calculators,
and your favorite bird, but friends and other human beings are not
permitted!


Relevant material of the Russel textbook:
Chapter 3 (with the exception of 3.7)
Chapter 4 (with the exception of 4.3)
Sections 5.1, 5.2, 5.3, 5.4, and 5.5.
Chapter 18 (excluding 18.5 and 18.6)
Sections 19.1, 19.2, 19.3, 19.4, 19.5

All the transparencies that were discussed in class (except
those used in the first week) are relevant for the midterm exam.

Material that was discussed in class that is relevant
for the midterm exam (but not necessarily is discussed in
the textbook):

a) Backtracking algorithm
b) Simulated Annealling and Hill Climbing Algorithms
c) Evolutionary Computing has been removed from the review list;
   it will a topic in the final exam. 
d) N-fold crossvalidation, information gain heuristic, pruning,
   of decision trees, inductive learning in general, splitting heuristic

In general, the midterm exam will focus on the following 
topics: formulating search problems, finding heuristics
for search problems, "general" search algorithm, breadth first
search, uniform cost search, depth-first seach, backtracking,
best-first search, A*, hill climbing, simulated annealing; 
inductive learning, in depth knowledge decision
trees, neural networks, give a neural
network that computes a particular function, have some idea
how neural network learning works.