TNN
2010
13 years 6 months ago
2010
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
TNN
2010
13 years 6 months ago
2010
Abstract--Recurrent neural networks have become a prominent tool for optimizations including linear or nonlinear variational inequalities and programming, due to its regular mathem...
TNN
2010
13 years 6 months ago
2010
Abstract--In this paper we investigate the sparsity and recognition capabilities of two approximate Bayesian classification algorithms, the multi-class multi-kernel Relevance Vecto...
TNN
2010
13 years 6 months ago
2010
Statistical learning methods are emerging as a valuable tool for decoding information from neural imaging data. The noisy signal and the limited number of training patterns that ar...
TNN
2010
13 years 6 months ago
2010
A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in...
TNN
2010
13 years 6 months ago
2010
Abstract--In this paper, the problem of stochastic synchronization analysis is investigated for a new array of coupled discretetime stochastic complex networks with randomly occurr...
TNN
2010
13 years 6 months ago
2010
Finite mixture model is a powerful tool in many statistical learning problems. In this paper, we propose a general, structure-preserving approach to reduce its model complexity, w...
TNN
2010
13 years 6 months ago
2010
In recent years, learning from imbalanced data has attracted growing attention from both academia and industry due to the explosive growth of applications that use and produce imba...
TNN
2010
2010
Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks
13 years 6 months ago
This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high...
TNN
2010
13 years 6 months ago
2010
We propose a multiple incremental decremental algorithm of Support Vector Machine (SVM). Conventional single incremental decremental SVM can update the trained model efficiently w...