In this paper we focus on the memory retrieval mechanism in an artificial neural network and suggest an algorithm to increase the memory retrieval rate in the BMatrix neural network. B-matrix is a model of recall by index, where in the activity spreads locally. The B-matrix approach to neural network function accounts for spreading of activity from one region to others based on adjacency of neu...

The use of artificial outputs generated by a classifier simulator has recently emerged as a new trend to provide an underlying evaluation of classifier combination methods. In this paper, we propose a new method for the artificial generation of classifier outputs based on additional parameters which provide sufficient diversity to simulate, for a problem of any number of classes and any type of...

The existing physical layer security algorithm, which is based on artificial noise, could affect legitimate receivers negatively when the number of users is no less than sending antennas in multi-user MIMO system. In order to improve security of multi-user MIMO system under this scenario, we propose a new multi-user MIMO system physical layer security algorithm based on joint channel state matr...

It is well known that in misspecified parametric models, the maximum likelihood estimator (MLE) is consistent for the pseudo-true value and has an asymptotically normal sampling distribution with "sandwich" covariance matrix. Also, posteriors are asymptotically centered at the MLE, normal and of asymptotic variance that is in general different than the sandwich matrix. It is shown that due to t...

The use of artificial outputs generated by a classifier simulator has recently emerged as a new trend to provide an underlying evaluation of classifier combination methods. In this paper, we propose a new method for the artificial generation of classifier outputs based on additional parameters which provide sufficient diversity to simulate, for a problem of any number of classes and any type of...

This paper describes a method for accelerating large scale Artificial Neural Networks (ANN) training using multi-GPUs by reducing the forward and backward passes to matrix multiplication. We propose an out-of-core multi-GPU matrix multiplication and integrate the algorithm with the ANN training. The experiments demonstrate that our matrix multiplication algorithm achieves linear speedup on mult...

In this paper we study the effect of the use of the consistent mass matrix when solving scalar nonlinear conservation equations. It is shown that a continuous finite element method based on artificial viscosity in space and explicit time stepping using the consistent mass matrix cannot satisfy the maximum principle.