This paper proposes a non-recurrent training algorithm, resilient propagation, for the Simultaneous Recurrent Neural network operating in relaxation-mode for computing high quality solutions of static optimization problems. Implementation details related to adaptation of the recurrent neural network weights through the non-recurrent training algorithm, resilient backpropagation, are formulated ...

neural network algorithms have been applied to a variety of areas of engineering and microwave structures. Neural networks are also able to model nonlinear relations between different data sets. Owing to this feature, an introduced neural network model (INN) based on particle swarm optimization (PSO) training algorithm (INN-PSO) is presented for pseudomorphic high electron mobility transistor (...

The problem of maximum likelihood decoding with a neural decoder for error-correcting code is considered. It shown that the can be improved two novel loss terms on node’s activations. first term imposes sparse constraint Whereas, second tried to mimic activations from teacher which has better performance. proposed method same run time complexity and model size as Belief Propagation decoder, whi...

In this paper, the gain in LD-CELP speech coding algorithm is predicted using three neural models, that are equipped by genetic and particle swarm optimization (PSO) algorithms to optimize the structure and parameters of neural networks. Elman, multi-layer perceptron (MLP) and fuzzy ARTMAP are the candidate neural models. The optimized number of nodes in the first and second hidden layers of El...

Aim of this contribution is to present the optimization of the laser cutting process by artificial neural networks. NeuroSolution for Excel 1.02 was used in order to interpret complicated dependencies between technological characteristics of laser cutting and output parameters. Multilayer feed forward neural networks are utilized for modelling and prediction of input parameters of laser cutting...