The Adaptive Solutions CN APS architecture chip is a general purpose neurocomputer chip. It has 64 processors, each with 4 K bytes of local memory, running at 25 megahertz. It is capable of implementing most current neural network algorithms with on chip learning. This paper discusses the implementation of the Back Propagation algorithm on an array of these chips and shows performance figures f...

Presently, one of the main issues to create challenges in medicine sciences by developing technology is the disease diagnosis with high accuracy. An automatic system is developed that classifies the thyroid nodule images using machine learning algorithms. Ultrasound imaging is the best way to prediction of which type of thyroid is there. Ultrasound thyroid Nodules images were distinguishing in ...

In this paper we show different evolutionary algorithms applied to the simultaneous off-line evolution of weights and transfer functions of feed-forward neural networks. Experimentation has been carried out with classical benchmarks when weights and both weights and transfer function are evolved and a comparison of the proposed evolutionary methods with classical methodologies (the back-propaga...

This paper presents an application of multilayered feed-forward neural networks for controlling a PT326 Process Trainer laboratory equipment. Firstly, the process as well as its inverse have been identi ed using the back-propagation (BP) algorithm for neural network training. Secondly an internal model control (IMC) strategy has been used for neurocontrol. Di erent architectures and learning me...

Since past few years, researchers have been concentrating on the classification of Electromyography Signal. This method is very convenient in diagnosing the neuro-muscular disorders, which consists of wide spread diseases affecting peripheral nervous system. Progressive muscle weakness is the major form of these disorders. Out of various proposed methods, scholars are commonly focusing on Neura...

In this paper we summarize some experiments we have carried out in order to classify mass spectra. First we describe the pre-processing and the features extraction we have realized using the Bioinformatics toolbox of MATLAB. Then we describe results we have obtained using feed forward neural networks trained with a classical back-propagation; to avoid reinventing the wheel, WEKA has been used f...

In this paper, an efficient approach for the recognition of online Arabic handwritten characters is presented. The method employed involves three phases: First, pre-processing in which the original image is transformed into a binary image .Second , training neural networks with feed-forward back propagation algorithm .Finally, the recognition of the character through the use of Neural Network t...

Automated attendance management system using face recognition is a smart way of marking attendance which is more secure and time efficient as compared to already existing attendance systems. In our work we propose an automated attendance management system. This system automatically detects the student when he enters the class room and marks the attendance by recognizing his face. A threshold va...

The universal asymptotic scaling laws proposed by Amari et al. are studied in large scale simulations using a CM5. Small stochastic multi-layer feed-forward networks trained with back-propagation are investigated. In the range of a large number of training patterns t, the asymptotic generalization error scales as 1=t as predicted. For a medium range t a faster 1=t 2 scaling is observed. This ee...

This paper presented the Minimal Radial Basis Function Network (MRBFN) approach busbar protection. The Optical Current Transducer (OCT) is used to solve the magnetic saturation so as to improve the reliability of the system. Performance of this model is compared with Feed Forward Back Propagation Neural Network (FFBP). The proposed model is more accurate in prediction with few numbers of hidden...