Learning with Product Units

Laurens R. Leerink, C. Lee Giles, Bill G. Home, Marwan A. Jabri

Research output: Contribution to conferencePaperpeer-review

37 Scopus citations


Product units provide a method of automatically learning the higher-order input combinations required for efficient learning in neural networks. However, we show that problems are encountered when using backpropagation to train networks containing these units. This paper examines these problems, and proposes some atypical heuristics to improve learning. Using these heuristics a constructive method is introduced which solves well-researched problems with significantly less neurons than previously reported. Secondly, product units are implemented as candidate units in the Cascade Correlation (Fahlman & Lebiere, 1990) system. This resulted in smaller networks which trained faster than when using sigmoidal or Gaussian units.

Original languageEnglish (US)
Number of pages8
StatePublished - 1994
Event7th International Conference on Neural Information Processing Systems, NIPS 1994 - Denver, United States
Duration: Jan 1 1994Jan 1 1994


Conference7th International Conference on Neural Information Processing Systems, NIPS 1994
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Signal Processing
  • Computer Networks and Communications


Dive into the research topics of 'Learning with Product Units'. Together they form a unique fingerprint.

Cite this