Sciweavers

TNN
2008
95views more  TNN 2008»
13 years 4 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
TNN
2008
143views more  TNN 2008»
13 years 4 months ago
Blur Identification by Multilayer Neural Network Based on Multivalued Neurons
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of spe...
Igor N. Aizenberg, Dmitriy Paliy, Jacek M. Zurada,...
TNN
2008
178views more  TNN 2008»
13 years 4 months ago
IMORL: Incremental Multiple-Object Recognition and Localization
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
Haibo He, Sheng Chen
TNN
2008
171views more  TNN 2008»
13 years 4 months ago
Adaptive Dynamic Inversion via Time-Scale Separation
Abstract--This paper presents a full state feedback adaptive dynamic inversion method for uncertain systems that depend nonlinearly upon the control input. Using a specialized set ...
Naira Hovakimyan, E. Lavretsky, Chengyu Cao
TNN
2008
100views more  TNN 2008»
13 years 4 months ago
Global Asymptotic Stability of Recurrent Neural Networks With Multiple Time-Varying Delays
In this paper, several sufficient conditions are established for the global asymptotic stability of recurrent neural networks with multiple time-varying delays. The Lyapunov
Huaguang Zhang, Zhanshan Wang, Derong Liu
TNN
2008
97views more  TNN 2008»
13 years 4 months ago
Training Hard-Margin Support Vector Machines Using Greedy Stagewise Algorithm
Hard-margin support vector machines (HM-SVMs) suffer from getting overfitting in the presence of noise. Soft-margin SVMs deal with this problem by introducing a regularization term...
Liefeng Bo, Ling Wang, Licheng Jiao
TNN
2008
124views more  TNN 2008»
13 years 4 months ago
Just-in-Time Adaptive Classifiers - Part II: Designing the Classifier
Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolu...
Cesare Alippi, Manuel Roveri
TNN
2008
128views more  TNN 2008»
13 years 4 months ago
A Hybrid Technique for Blind Separation of Non-Gaussian and Time-Correlated Sources Using a Multicomponent Approach
Blind inversion of a linear and instantaneous mixture of source signals is a problem often encountered in many signal processing applications. Efficient FastICA (EFICA) offers an ...
Petr Tichavský, Zbynek Koldovský, Ar...
TNN
2008
177views more  TNN 2008»
13 years 4 months ago
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting...
Yoshua Bengio, Jean-Sébastien Senecal
TNN
2008
78views more  TNN 2008»
13 years 4 months ago
Automatic Relevance Determination for Identifying Thalamic Regions Implicated in Schizophrenia
There have been many theories about and computational models of the schizophrenic disease state. Brain imaging techniques have suggested that abnormalities of the thalamus may con...
Antony Browne, Angela Jakary, S. Vinogradov, Yu Fu...