This page, http://www.cs.uiowa.edu/~hzhang/c145/, is always under construction.
|
Instructor:
Hantao Zhang
Office: 201B MLH, Email: hzhang@cs.uiowa.edu, Tel: 353-2545 Office hours: MWF, 2:30-3:30 |
Teaching assistant:
Viet Thuc Ha
Office: 101N MLH, Email: hviet@cs.uiowa.edu, Tel: 335-2839 Office hours: Tu.Th. 10:30-12:00 |
Attention: No lecture on Friday, Oct. 3.
I need to hear from anyone who has a disability, which may require some
modification of seating, testing or other class requirements so that
appropriate arrangements may be made. Please contact me as soon as possible.
In addition, a number of class notes and handouts will be available through the course web site.
LATE-DUE HOMEWORK ARE NOT ACCEPTED.
For homeworks involving programming, please hand in a listing of your
code and a transcipt of a sample run. Please also send a copy of your
code by email to both TA and the instructor.
Sample answer to 11.4: monkeys.pl
The remaining of this homework is a small programming project in Prolog: You are asked to implement Choose-Attribute in the function Decision-Tree-Learning in Figure 18.5 (page 658).
The examples will be the data from Figure 18.3, which can be specified in Prolog as follows:
atributs([alt([y,n]),
bar([y,n]),
fri([y,n]),
hun([y,n]),
pat([none,some,full]),
price([chea,medi,expe]),
rain([y,n]),
res([y,n]),
type([burger,french,italian,thai]),
est([w1,w2,w3,4])
]).
examples([x1([y,n,n,y,some,expe,n,y,french, w1], y),
x2([y,n,n,y,full,chea,n,n,thai, w3], n),
x3([n,y,n,n,some,chea,n,n,burger, w1], y),
x4([y,n,y,y,full,chea,y,n,thai, w2], y),
x5([y,n,y,n,full,expe,n,y,french, w4], n),
x6([n,y,n,y,some,medi,y,y,italian,w1], y),
x7([n,y,n,n,none,chea,y,n,burger, w1], n),
x8([n,n,n,y,some,medi,y,y,thai, w1], y),
x9([n,y,y,n,full,chea,y,n,burger, w4], n),
x10([y,y,y,y,full,expe,n,y,italian,w2], n),
x11([n,n,n,n,none,chea,n,n,thai, w1], n),
x12([y,y,y,y,full,chea,n,n,burger, w3], y)]).
You need to write a function to compute the information Gain
for all the atributes and then return one with the maximum gain.
FOR THE POLICY ON CHEATING, SEE THE GRADUATE
HANDBOOK OF THE DEPARTMENT OF COMPUTER SCIENCE.
You are expected to study all the material in each chapter covered in the readings even if that material is not explicitly discussed in class or in the homework. You are also expected to study the extra material presented in class which is not in the textbook. Material presented in class, but not in the book may appear on tests.
The lecture notes are a supplement to the course textbook. They are supposed to help you understand the textbook material better, they are not a replacement for either the textbook or the lecture itself.