Sciweavers

978 search results - page 5 / 196
» Some neural networks compute, others don't
Sort
View
IJCNN
2008
IEEE
14 years 2 months ago
Biologically realizable reward-modulated hebbian training for spiking neural networks
— Spiking neural networks have been shown capable of simulating sigmoidal artificial neural networks providing promising evidence that they too are universal function approximat...
Silvia Ferrari, Bhavesh Mehta, Gianluca Di Muro, A...
NC
2011
201views Neural Networks» more  NC 2011»
13 years 2 months ago
The computational power of membrane systems under tight uniformity conditions
We apply techniques from complexity theory to a model of biological cellular membranes known as membrane systems or P-systems. Like Boolean circuits, membrane systems are defined ...
Niall Murphy, Damien Woods
CJ
2008
108views more  CJ 2008»
13 years 7 months ago
Computing with Time: From Neural Networks to Sensor Networks
This article advocates a new computing paradigm, called computing with time, that is capable of efficiently performing a certain class of computation, namely, searching in paralle...
Boleslaw K. Szymanski, Gilbert Chen
NN
2007
Springer
13 years 7 months ago
Edge of chaos and prediction of computational performance for neural circuit models
We analyze in this article the significance of the edge of chaos for real-time computations in neural microcircuit models consisting of spiking neurons and dynamic synapses. We ...
Robert A. Legenstein, Wolfgang Maass
NC
2011
236views Neural Networks» more  NC 2011»
12 years 10 months ago
Graph multiset transformation: a new framework for massively parallel computation inspired by DNA computing
In this paper, graph multiset transformation is introduced and studied as a novel type of parallel graph transformation. The basic idea is that graph transformation rules may be ap...
Hans-Jörg Kreowski, Sabine Kuske