In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the Hopfield neural network, whereas the performance of a sparsely connected winner-take-all neural n...

After more than a decade of research, there now exist several neural-network techniques for solving NP-hard combinatorial optimization problems. Hopfield networks and selforganizing maps are the two main categories into which most of the approaches can be divided. Criticism of these approaches includes the tendency of the Hopfield network to produce infeasible solutions, and the lack of general...

After more than a decade of research, there now exist several neural-network techniques for solving NP-hard combinatorial optimization problems. Hopfield networks and self-organizing maps are the two main categories into which most of the approaches can be divided. Criticism of these approaches includes the tendency of the Hopfield network to produce infeasible solutions, and the lack of genera...

Under proper conditions, a globular protein adopts a unique three-dimensional structure that is encoded in this amino acid sequence. The theoretical prediction of this structure, and the pathways followed during the folding process constitute the most challenging and still unsolved problems of structural molecular biology. Computersimulated neural networks have recently gained much attention an...

Neural networks have been widely applied in image processing, pattern recognition, optimization solvers, fixed-point computation and other engineering areas. It has been known that these applications heavily depend on the dynamic behaviors of neural networks. The stability of neural networks has been extensively studied over the past years because it is one of the most important behaviors of ne...

The stability and convergence of the neural networks are the fundamental characteristics in the Hopfield type networks. Since time delay is ubiquitous in most physical and biological systems, more attention is being made for the delayed neural networks. The inclusion of time delay into a neural model is natural due to the finite transmission time of the interactions. The stability analysis of t...

This paper presents a novel approach to the emulation of locomotor central pattern generators (CPGs) of legged animals. Based on Scheduling by Multiple Edge Reversal (SMER), a simple but powerful distributed algorithm, it is shown how oscillatory building blocks (OBBs) can be created and how OBB-based networks can be implemented as asymmetric Hopfield-like neural networks for the generation of ...

This paper considers the global exponential stability of delay neural networks with impulsive perturbations. By establishing a new impulsive delay inequality which is different from the earlier publication, we obtain some new sufficient conditions ensuring exponential stability of the equilibrium point for such neural networks. The neural networks model considered include the impulsive delay Ho...

A neural network which is recognized as artificial neural network is a mathematical model or computational model that tries to simulate the structure and functional aspect of biological neural networks. It can solve complicated recognition solve optimization problems and analysis problems. It is because it composed of huge amount of interconnected neurons to solve specific problems [1]. Hopfiel...

Matt Stowe and Subhash Kak . Abstract: This paper examines the memory capacity of generalized neural networks. Hopfield networks trained with a variety of learning techniques are investigated for their capacity both for binary and non-binary alphabets. It is shown that the capacity can be much increased when multilevel inputs are used. New learning strategies are proposed to increase Hopfield n...