Adaptability of the backpropagation procedure

Nathalie Japkowicz, Stephen Jose Hanson

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations

Abstract

Possible paradigms for concept learning by feedforward neural networks include discrimination and recognition. An interesting aspect of this dichotomy is that the recognition-based implementation can learn certain domains much more efficiently than the discrimination-based one, despite the close structural relationship between the two systems. The purpose of this paper is to explain this difference in efficiency. We suggest that it is caused by a difference in the generalization strategy adopted by the Backpropagation procedure in both cases: while the autoassociator uses a (fast) bottom-up strategy, MLP has recourse to a (slow) top-down one, despite the fact that the two systems are both optimized by the Backpropagation procedure. This result is important because it sheds some light on the nature of Backpropagation's adaptative capability. From a practical viewpoint, it suggests a deterministic way to increase the efficiency of Backpropagation-trained feedforward networks.

Original languageEnglish (US)
Pages1710-1715
Number of pages6
StatePublished - 1999
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: Jul 10 1999Jul 16 1999

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period7/10/997/16/99

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Adaptability of the backpropagation procedure'. Together they form a unique fingerprint.

Cite this