Title :
Test cases: emergent generalizations in the Athena and the Rumelhart´s neural net models
Author :
Srikanth, Radhakrishnan ; Koutsougeras, Cris ; Bringman, M.W. ; Dandashi, Fatma
Author_Institution :
Dept. of Comput. Sci., Tulane Univ., New Orleans, LA, USA
Abstract :
The performances of Rumelhart´s nonlinear feedforward (NLFF) model and Athena are compared with respect to their generalization capabilities. The evaluation is based on a number of actual test cases. Evaluations are provided for the specific characteristics of the problems and the models involved, explaining the variations of their performances. The test cases presented illustrate the general type of problems which are particular to each model. The models have been applied on a few different types of learning tasks
Keywords :
learning systems; neural nets; Athena; Rumelhart´s neural net models; learning tasks; nonlinear feedforward model; performance comparison; Computer aided software engineering; Computer science; Feedforward systems; Information retrieval; Neural networks; Performance evaluation; Testing; Wave functions;
Conference_Titel :
Southeastcon '90. Proceedings., IEEE
Conference_Location :
New Orleans, LA
DOI :
10.1109/SECON.1990.117864
