Sciweavers

1512 search results - page 106 / 303
» connection 2006
Sort
View
IJON
2000
71views more  IJON 2000»
15 years 6 months ago
Variable selection using neural-network models
In this paper we propose an approach to variable selection that uses a neural-network model as the tool to determine which variables are to be discarded. The method performs a bac...
Giovanna Castellano, Anna Maria Fanelli
IJON
2000
73views more  IJON 2000»
15 years 6 months ago
A recurrent network model for the phase invariance of complex cell responses
Cortical amplification is a mechanism for modifying the selectivity of neurons through recurrent interactions. Although conventionally used to enhance selectivity, cortical amplif...
Frances S. Chance, Sacha B. Nelson, L. F. Abbott
IJON
2000
85views more  IJON 2000»
15 years 6 months ago
Hebbian learning and temporary storage in the convergence-zone model of episodic memory
The Convergence-Zone model shows how sparse, random memory patterns can lead to one-shot storage and high capacity in the hippocampal component of the episodic memory system. This...
Michael Howe, Risto Miikkulainen
IJON
2000
86views more  IJON 2000»
15 years 6 months ago
Gain modulation of recurrent networks
Gain modulation is an important mechanism by which attentional and other inputs modify the amplitude of neuronal responses without changing their selectivity. Gain modulation has ...
Jian Zhang 0004, L. F. Abbott
IJPRAI
2000
101views more  IJPRAI 2000»
15 years 6 months ago
An Integer Recurrent Artificial Neural Network for Classifying Feature Vectors
: The main contribution of this report is the development of an integer recurrent artificial neural network (IRANN) for classification of feature vectors. The network consists both...
Roelof K. Brouwer