TNN
2008
13 years 11 months ago
2008
Abstract--In this paper, we consider delayed bidirectional associative memory (BAM) neural networks (NNs) with Lipschitz continuous activation functions. By applying Young's i...
TNN
2008
14 years 13 hour ago
2008
Abstract--This paper investigates whether spike-timing-dependent plasticity (STDP) can minimize the effect of mismatch within the context of a depth-from-motion algorithm. To impro...
TNN
2008
14 years 14 days ago
2008
Abstract--The stationarity requirement for the process generating the data is a common assumption in classifiers' design. When such hypothesis does not hold, e.g., in applicat...
TNN
2008
14 years 14 days ago
2008
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
TNN
2008
14 years 14 days ago
2008
In this paper, we introduce a novel way of performing real-valued optimization in the complex domain. This framework enables a direct complex optimization technique when the cost f...
TNN
2008
14 years 14 days ago
2008
In this paper, spiking neuronal models employing means, variances, and correlations for computation are introduced. We present two approaches in the design of spiking neuronal netw...
TNN
2008
14 years 14 days ago
2008
This paper presents a novel recurrent neural network for solving nonlinear optimization problems with inequality constraints. Under the condition that the Hessian matrix of the ass...
TNN
2008
14 years 14 days ago
2008
Abstract--This paper considers the approximation of sufficiently smooth multivariable functions with a multilayer perceptron (MLP). For a given approximation order explicit formula...
TNN
2008
14 years 14 days ago
2008
TNN
2008
14 years 14 days ago
2008
In classical training methods for node open fault, we need to consider many potential faulty networks. When the multinode fault situation is considered, the space of potential faul...