Sciweavers

715 search results - page 43 / 143
» Neural Network with Matrix Inputs
Sort
View
TNN
2008
95views more  TNN 2008»
13 years 8 months ago
A Constrained Optimization Approach to Preserving Prior Knowledge During Incremental Training
In this paper, a supervised neural network training technique based on constrained optimization is developed for preserving prior knowledge of an input
Silvia Ferrari, Mark Jensenius
CSL
2007
Springer
13 years 8 months ago
Modeling durations of syllables using neural networks
In this paper, we propose a neural network model for predicting the durations of syllables. A four layer feedforward neural network trained with backpropagation algorithm is used ...
K. Sreenivasa Rao, B. Yegnanarayana
IJCNN
2006
IEEE
14 years 2 months ago
On derivation of stagewise second-order backpropagation by invariant imbedding for multi-stage neural-network learning
— We present a simple, intuitive argument based on “invariant imbedding” in the spirit of dynamic programming to derive a stagewise second-order backpropagation (BP) algorith...
Eiji Mizutani, Stuart Dreyfus
ICANN
2005
Springer
14 years 2 months ago
Training of Support Vector Machines with Mahalanobis Kernels
Abstract. Radial basis function (RBF) kernels are widely used for support vector machines. But for model selection, we need to optimize the kernel parameter and the margin paramete...
Shigeo Abe
RECOMB
2004
Springer
14 years 9 months ago
A class of edit kernels for SVMs to predict translation initiation sites in eukaryotic mRNAs
The prediction of translation initiation sites (TISs) in eukaryotic mRNAs has been a challenging problem in computational molecular biology. In this paper, we present a new algori...
Haifeng Li, Tao Jiang