Skip to Main content Skip to Navigation
Journal articles

Solving Time of Least Square Systems in Sigma-Pi Unit Networks

Abstract : The solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the solution must be obtained on-line, thus the time required to solve a system in a plausible neural architecture is critical. This paper presents a recurrent network of Sigma-Pi neurons, whose solving time increases at most like the logarithm of the system size, and of its condition number, which provides plausible computation times for biological systems.
Document type :
Journal articles
Complete list of metadatas
Contributor : Pierre Courrieu <>
Submitted on : Tuesday, April 29, 2008 - 7:07:14 PM
Last modification on : Tuesday, April 23, 2019 - 4:38:02 PM
Long-term archiving on: : Friday, May 28, 2010 - 6:02:57 PM


Publisher files allowed on an open archive


  • HAL Id : hal-00276480, version 1
  • ARXIV : 0804.4808



Pierre Courrieu. Solving Time of Least Square Systems in Sigma-Pi Unit Networks. Neural Information Processing - Letters and Reviews, KAIST Press, 2004, 4 (3), pp.39-45. ⟨hal-00276480⟩



Record views


Files downloads