Sciweavers

17 search results - page 1 / 4
» On the selection of weight decay parameter for faulty networ...
Sort
View
TNN
2010
168views Management» more  TNN 2010»
13 years 1 months ago
On the selection of weight decay parameter for faulty networks
The weight-decay technique is an effective approach to handle overfitting and weight fault. For fault-free networks, without an appropriate value of decay parameter, the trained ne...
Andrew Chi-Sing Leung, Hongjiang Wang, John Sum
CORR
2008
Springer
179views Education» more  CORR 2008»
13 years 7 months ago
Distributed Parameter Estimation in Sensor Networks: Nonlinear Observation Models and Imperfect Communication
The paper studies the problem of distributed static parameter (vector) estimation in sensor networks with nonlinear observation models and imperfect inter-sensor communication. We...
Soummya Kar, José M. F. Moura, Kavita Raman...
IJCNN
2006
IEEE
14 years 1 months ago
Leave-One-Out Cross-Validation Based Model Selection Criteria for Weighted LS-SVMs
Abstract— While the model parameters of many kernel learning methods are given by the solution of a convex optimisation problem, the selection of good values for the kernel and r...
Gavin C. Cawley
ISCAS
2006
IEEE
84views Hardware» more  ISCAS 2006»
14 years 1 months ago
Programmable synaptic weights for an aVLSI network of spiking neurons
—We describe a spiking neuronal network which allows local synaptic weights to be assigned to individual synapses. In previous implementations of neuronal networks, the biases th...
Yingxue Wang, Shih-Chii Liu
NIPS
1990
13 years 8 months ago
Back Propagation is Sensitive to Initial Conditions
This paper explores the effect of initial weight selection on feed-forward networks learning simple functions with the back-propagation technique. We first demonstrate, through th...
John F. Kolen, Jordan B. Pollack