We study the recognition capabilities of Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. show that such at zero temperature outperform those original model, due to substantial increase storage capacity and lack defined basin attraction. The modified does not fall abruptly into regime complete confusion when memory load exceeds shar...

A specific type of neural networks, the Restricted Boltzmann Machines (RBM), are implemented for classification and feature detection in machine learning. They are characterized by separate layers of visible and hidden units, which are able to learn efficiently a generative model of the observed data. We study a "hybrid" version of RBMs, in which hidden units are analog and visible units are bi...

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...

J. J. Hopfield, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities,” Proc. Nat. Acad. Sci., USA, vol. 79, pp. 2254-2258, Apr. 1982. R. J. McEliece, et al., “The Capacity of the Hopfield Associative Memory,” IEEE Transactions on Information Theory, vol. T-33, pp. 461-482, 1987. B. L. Montgomery et al., “Evaluation of the use of Hopfield Neural Network Model as...

Abstract − The asymptotic behavior of a class discrete-time Hopfield neural network is studied in this paper. Some properties for this class discrete-time neural network, such as the boundedness of motion trajectory, the uniqueness and the absolute stability of equilibrium point etc, are obtained. In this paper, the sufficient conditions related to the existence of unique equilibrium point and ...

With the complexity increase in industrial production process, the traditional ProportionIntegration-Differentiation (PID) control can not meet the requirements of the control system performance. Because neural network has the ability of adaptive, self-learning and nonlinear function approximation, control equality of system is improved if it is combined with traditional PID. In the paper, Hopf...

For the Hopfield model with the Hebb connection matrix we investigate the case of p memorized patterns that are distorted copies of the same standard. In other words, we try to simulate that learning always takes place by means of repeating presentations of one and the same standard, and the presentations are accompanied by distortions of the standard. We obtain some rigorous results relating t...

Optical implementation of content addressable associative memory based on the Hopfield model for neural networks and on the addition of nonlinear iterative feedback to a vector-matrix multiplier is described. Numerical and experimental results presented show that the approach is capable of introducing accuracy and robustness to optical processing while maintaining the traditional advantages of ...