Sciweavers

492 search results - page 17 / 99
» Neuronal Models with Current Inputs
Sort
View
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
14 years 3 months ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
NIPS
2003
13 years 11 months ago
Nonlinear Processing in LGN Neurons
According to the current standard model, neurons in lateral geniculate nucleus (LGN) operate linearly. There is, however, ample evidence that LGN responses are nonlinear. To accou...
Vincent Bonin, Valerio Mante, Matteo Carandini
ISCAS
2006
IEEE
162views Hardware» more  ISCAS 2006»
14 years 3 months ago
Silicon neurons that phase-lock
Abstract—We present a silicon neuron with a dynamic, active leak that enables precise spike-timing with respect to a time-varying input signal. Our neuron models the mammalian bu...
J. H. Wittig Jr., Kwabena Boahen
NPL
2006
85views more  NPL 2006»
13 years 9 months ago
A Neural Model for Context-dependent Sequence Learning
A novel neural network model is described that implements context-dependent learning of complex sequences. The model utilises leaky integrate-and-fire neurons to extract timing inf...
Luc Berthouze, Adriaan G. Tijsseling
IWINAC
2005
Springer
14 years 3 months ago
Interacting Slow and Fast Dynamics in Precise Spiking-Bursting Neurons
We have explored the role of the interaction of slow and fast intracellular dynamics in generating precise spiking-bursting activity in a model of the heartbeat central pattern gen...
Fabiano Baroni, Joaquín J. Torres, Pablo Va...