Nonlinear system identification via Feedforward Neural Networks (FNN) and Digital Recurrent Network (DRN) is studied in this paper. The standard backpropagation algorithm is used to train the FNN. A dynamic backpropagation algorithm is employed to adapt weights and biases of the DRN. The neural networks are trained using the identified error between the model’s output and plant’s output. Result...

Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohon...

A fuzzy neural network and its relevant fuzzy neuron and fuzzy learning algorithm are introduced. An object-oriented implementation of fuzzy neural network in MATLAB environment is realized. Simulations are carried out by SIMULINK. The performance of fuzzy neural network is experimentally compared with other neural networks trained by backpropagation algorithms. It shows better convergence spee...

We apply a neural network to model neural network learning algorithm itself. The process of weights updating in neural network is observed and stored into file. Later, this data is used to train another network, which then will be able to train neural networks by imitating the trained algorithm. We use backpropagation algorithm for both, for training, and for sampling the training process. We i...

Standard error backpropagation is used in almost all modern deep network training. However, it typically suffers from proliferation of saddle points in high-dimensional parameter space. Therefore, it is highly desirable to design an efficient algorithm to escape from these saddle points and reach a good parameter region of better generalization capabilities, especially based on rough insights a...

This paper presents a constructive approach to neural network modeling of polynomial harmonic functions. This is an approach to growing higher-order networks like these build by the multilayer GMDH algorithm using activation polynomials. Two contributions for enhancement of the neural network learning are offered: (1) extending the expressive power of the network representation with another com...

The article deals with a WAN switch design based on a Feedforward neural network, specifically for the Feedforward Backpropagation algorithm. The designed switch is fully parallel, uses neural network for switch management and also for traffic engineering. The switch uses advanced packet dropping mechanism. The article describes the switch design (network processor design) and compares the deve...

Deep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, recent works have shown that models with much smaller number of parameters can also perform just as well. In this work, we introduce the problem of architecture-learning, i.e; learning the architecture of a neural network along with weights. We start with a large ne...

Face recognition is a system that identifies human faces through complex computational techniques. The paper explains two different algorithms for feature extraction. These are Principal Component Analysis and Fisher Faces algorithm. It then explains how images can be recognized using a backpropagation algorithm on a feed forward neural network. Two training databases one containing 20 images a...

We show on an example from medical diagnosis that some problems can be solved using simple neural networks. First we define some basic notions from neural network theory. We mention also some basic facts about electrocardiography. Then we use three-layered neural network with backpropagation algorithm to adaptation on classification the patients' ECG signals into two classes and summarize results.