A generalized-statistics variational principle for source separation is formulated by recourse to Tsallis’ entropy subjected to the additive duality and employing constraints described by normal averages. The variational principle is amalgamated with Hopfield-like learning rules resulting in an unsupervised learning model. The update rules are formulated with the aid of q-deformed calculus. Num...

We study filter–based feature selection methods for classification of biomedical images. For feature selection, we use two filters — a relevance filter which measures usefulness of individual features for target prediction, and a redundancy filter, which measures similarity between features. As selection method that combines relevance and redundancy we try out a Hopfield network. We experimenta...

This paper studies Hopfield neural networks from the perspective of self-stabilizing distributed computation. Known self-stabilization results on Hopfield networks are surveyed. Key ingredients of the proofs are given. Novel applications of self-stabilization—associative memories and optimization—arising from the context of neural networks are discussed. Two new results at the intersection of H...

Stereo-correspondence is the most important issue in stereopsis. Feature extraction and matching are the basic steps involved in the solution of stereocorrespondence problem. This work examines the effectiveness of Gabor Logons as pre-processing technique compared to intensity image. The matching is performed using Hopfield network and Simulated Annealing. Performance of these matching techniqu...

We rigorously establish a close relationship between message passing algorithms and models of neurodynamics by showing that the equations of a continuous Hopfield network can be derived from the equations of belief propagation on a binary Markov random field. As Hopfield networks are equipped with a Lyapunov function, convergence is guaranteed. As a consequence, in the limit of many weak connec...

Present paper demonstrates on innovative approach for a fundamental problem in computer vision to map real time a pixel in one image to a pixel on another image of the same scene, which is generally called image correspondence problem. It is a novel real time image matching method which combines Rotational Invariant Feature Selection for real time images and optimization capabilities of Hopfiel...

This paper presents real power optimization with load flow using an adaptive Hopfield neural network. In order to speed up the convergence of the Hopfield neural network system, the two adaptive methods, slope adjustment and bias adjustment, were used with adaptive learning rates. Algorithms of economic load dispatch for piecewise quadratic cost functions using the Hopfield neural network have ...

In this paper we are studying the tolerance of Hopfield neural network for storage and recalling of fingerprint images. The feature extraction of these images is performed with FFT, DWT and SOM. These feature vectors are stored as associative memory in Hopfield Neural Network with Hebbian learning and Pseudoinverse learning rules. The objective of this study is to determine the optimal weight m...

The idea of Hopfield network is based on the king spin glass model in which each spin has only two possible states: up and down. By introducing stochastic factors into this network and performing a simulated annealing process on it, it becomes a Boltzmann machine which can escape from local minimum states to achieve the global minimum. This paper generalizes the above ideas to multi-value case ...