Abstract
Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.
Original language | English |
---|---|
Title of host publication | ICSC International Symposium on Soft Computing |
Publisher | Millet : ICSC Academic Press |
Publication status | Published - Dec 31 1997 |
Event | SOCO'97 - Nîmes, France Duration: Sept 17 1997 → … |
Conference
Conference | SOCO'97 |
---|---|
Period | 9/17/97 → … |