Sciweavers

715 search results - page 26 / 143
» Neural Network with Matrix Inputs
Sort
View
NIPS
1998
13 years 10 months ago
Computational Differences between Asymmetrical and Symmetrical Networks
Symmetrically connected recurrent networks have recently been used as models of a host of neural computations. However, biological neural networks have asymmetrical connections, at...
Zhaoping Li, Peter Dayan
ISNN
2007
Springer
14 years 3 months ago
Regularized Alternating Least Squares Algorithms for Non-negative Matrix/Tensor Factorization
Nonnegative Matrix and Tensor Factorization (NMF/NTF) and Sparse Component Analysis (SCA) have already found many potential applications, especially in multi-way Blind Source Separ...
Andrzej Cichocki, Rafal Zdunek
ICASSP
2011
IEEE
13 years 18 days ago
Localization of non-linguistic events in spontaneous speech by Non-Negative Matrix Factorization and Long Short-Term Memory
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detect...
Felix Weninger, Björn Schuller, Martin Wö...
ICANN
2005
Springer
14 years 2 months ago
New Ears for a Robot Cricket
Cricket females perform phonotaxis towards the specific sounds produced by male crickets. By means of a well-tuned peripheral auditory system the cricket is able to extract direct...
Ben Torben-Nielsen, Barbara Webb, Richard E. Reeve
ANNPR
2006
Springer
14 years 19 days ago
Support Vector Regression Using Mahalanobis Kernels
Abstract. In our previous work we have shown that Mahalanobis kernels are useful for support vector classifiers both from generalization ability and model selection speed. In this ...
Yuya Kamada, Shigeo Abe