Gennari, J.C., Langley, P., and Fisher, D. 1990. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Learning To Design Together - Dan Grecu David (Correct)
....phases: 1. Create a case from the interaction with agent B. A case is indexed by the design requirements which B considered in taking its decision. The contents of a case are the responses of agent B. Each case represents a training instance in developing a conceptual description of B s behavior [Gennari et al. 1990] [Michalski 1983] The concept features are the design conditions which led to B s proposal, expressed as allowable design ranges and thresholds. The contents of the proposal itself determines the class in which the concept falls (e.g, the material being objected to, if agent B is a critic) 2. ....
Gennari, J.C., Langley, P., and Fisher, D. 1990.
Conceptual Clustering in Structured Databases: a.. - Ketterlin.. (1995) (5 citations) (Correct)
....sub clusters, instead of a single class attribute. The original Cobweb algorithm was designed to deal with nominal attributes. In that case, the predictivity of an attribute is computed from the frequency count of each value of each attribute, which is stored in each cluster. The Classit algorithm (Gennari, Langley, Fisher 1989) extends this formalism to deal with numerical attributes, where an underlying normal distribution is assumed. The predictivity can thus be expressed as the inverse of the standard deviation. Any new type of attribute could be defined, as soon as a representation is provided for generalizations, ....
Gennari, J. H.; Langley, P.; and Fisher, D. H. 1989.
Irrelevant Features and the Subset Selection Problem - John, Kohavi, Pfleger (1994) (270 citations) (Correct)
....and Dietterich (1991, p. 548) define relevance under the assumption that all features and the label are Boolean and that there is no noise. Definition 1 A feature X i is said to be relevant to a concept C if X i appears in every Boolean formula that represents C and irrelevant otherwise. Gennari et al. 1989, Section 5.5) define relevance as 1 1 The definition given is a formalization of their state Definition Relevant Irrelevant Definition 1 X 1 X 2 ; X 3 ; X 4 ; X 5 Definition 2 None All Definition 3 All None Definition 4 X 1 X 2 ; X 3 ; X 4 ; X 5 Table 1: Feature relevance for the Correlated ....
Gennari, J. H.; Langley, P.; and Fisher, D. 1989.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC