Sciweavers

87 search results - page 1 / 18
» Analog Computation Via Neural Networks
Sort
View
ISTCS
1993
Springer
13 years 9 months ago
Analog Computation Via Neural Networks
We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a xed structure, invariant in time...
Hava T. Siegelmann, Eduardo D. Sontag
NEUROSCIENCE
2001
Springer
13 years 9 months ago
Finite-State Computation in Analog Neural Networks: Steps towards Biologically Plausible Models?
Abstract. Finite-state machines are the most pervasive models of computation, not only in theoretical computer science, but also in all of its applications to real-life problems, a...
Mikel L. Forcada, Rafael C. Carrasco
CISS
2008
IEEE
13 years 11 months ago
Reconstruction of compressively sensed images via neurally plausible local competitive algorithms
Abstract—We develop neurally plausible local competitive algorithms (LCAs) for reconstructing compressively sensed images. Reconstruction requires solving a sparse approximation ...
Robert L. Ortman, Christopher J. Rozell, Don H. Jo...
NIPS
2004
13 years 6 months ago
Edge of Chaos Computation in Mixed-Mode VLSI - A Hard Liquid
Computation without stable states is a computing paradigm different from Turing's and has been demonstrated for various types of simulated neural networks. This publication t...
Felix Schürmann, Karlheinz Meier, Johannes Sc...
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
13 years 9 months ago
Bounds for the computational power and learning complexity of analog neural nets
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
Wolfgang Maass