Neural networks: implementations and applications (original) (raw)
Related papers
Proceedings Electronic Technology Directions to the Year 2000, 1995
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering. science and business. This paper presents the implementation of several neural network simulators and their applications in chnracter recognition and other engineering areas. This paper presents the implemenration of back propagabon, radial basis function, Kohonen net, ARTl, Hopfield net and BAM. Other applications are also presented. 2. Neural network simulations
CHARACTER AND NUMERICAL RECOGNITION SYSTEM USING FEED FORWARD AND BACK PROPAGATION NEURAL NETWORK
TJPRC, 2014
In this proposed system, a neural network for characters and digits recognition is proposed by using algorithms to the neural network. The neural network can effectively recognize various characters of different languages such as Tamil, Hindi, English Malayalam and other language characters and even digits with higher rate of accuracy of recognition can be built using the Neural Network. A Back Propagation (BP), Feed forward (FF) and classifying algorithm is capable of reducing the number of neurons correspondingly and increasing recognition rates for the fixed number of output. Neural Network (NN) is a computational model or mathematical model based on biological neural networks. There are various research are going on the recognition system using neural network bionic man is one of the best example for the application of the neural network. NN consists of an interconnected cluster of artificial neurons and which processes information using a connectionist approach to computation of the results. In certain cases NN is an adaptive system that changes its structure based on the internal and external information that flows through the network during the beginning phase (learning). They can be used to model complex relationships between number of outputs and inputs or it can able to find patterns in the given data. The simulations result has been provided for the verification and to see the performance of the recognition.
2013
Abstract: The aim of this paper is the presentation of a neural network simulator, the “Neural Workbench ”.The structure of this simulator is based on the principles of Object –Oriented Design. This facilitates the implementation of complicated neural network structures that can be used to address a variety of problems and applications. In addition to the description of the simulator structure, specific task screen-shots of the running application are presented, and typical network paradigms and examples are studied.
Artificial neural networks: a tutorial
Computer, 1996
Numerous e orts have been made in developing \intelligent" programs based on the Von Neumann's centralized architecture. However, these e orts have not been very successful in building general-purpose intelligent systems. Inspired by biological neural networks, researchers in a number of scienti c disciplines are designing arti cial neural networks (ANNs) to solve a variety of problems in decision making, optimization, prediction, and control. Arti cial neural networks can be viewed as parallel and distributed processing systems which consist of a huge number of simple and massively connected processors. There has been a resurgence of interest in the eld of ANNs for several years. This article intends to serve as a tutorial for those readers with little or no knowledge about ANNs to enable them to understand the remaining articles of this special issue. We discuss the motivations behind developing ANNs, basic network models, and two main issues in designing ANNs: network architecture and learning process. We also present one of the most successful application of ANNs, namely automatic character recognition.
Neural Network Based Handwritten Digits Recognition- An Experiment and Analysis
International Journal of Computer and Electrical Engineering, 2009
Handwritten digit recognition has become very useful in endeavors of human/computer interaction. Reliable, fast, and flexible recognition methodologies have elevated the utility. This paper presents an experiment and analysis of the Neural Network classifier to recognize handwritten digits based on a standard database. The experimental setup implemented in Matlab determines the ability of a Multi-Layer Neural Network to identify handwritten digit samples 5-9. This network is the representative for recognition of remaining digits 0-4. We consider not only accurate recognition rate, but also training time, recognition time as well as the complexity of the networks. The Multi-Layer Perceptron Network (MLPN) was trained by back propagation algorithm. Network structures vary with the hidden units, learning rates, the number of iterations that seem necessary for the network to converge. Different network structures and their corresponding recognition rates are compared in this paper to find the optimal parameters of the Neural Network for this application. Using the optimal parameters, the network performs with an overall recognition rate 94%.
Study of character recognition using neural network
National Conference on Role of ICT in Knowledge Management ( ICTKM-2012), 2012
The objective of this review paper is to discuss and compare some aspect of pattern recognition, among the various framework in which pattern recognition has been traditionally formulated. The primary goal of pattern recognition is supervised or unsupervised classification. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation.
Character Recognition Technique using Neural Network
2013
Character Recognition (CR) has been extensively studied in the last half century and progressed to a level, sufficient to produce technology driven applications. The preprocessing of characters comprises bounding of characters for translation invariance and normalization of characters for size invariance. Now, the rapidly growing computational power enables the implementation of the present CR methodologies and also creates an increasing demand on many emerging application domains, which require more advanced methodologies. In this paper an attempt is made to develop neural network strategies for the isolated. Handwritten English characters (A to Z. a to z). The preprocessing of characters comprises bounding of characters for translation invariance and normalization of characters for size invariance. First, an overview of CR systems and their evolution over time is presented. Then, the available CR techniques with their superiorities and weaknesses are reviewed. Finally, the current...
A Study on Character Recognition System Using Neural Network
Character recognition system is today’s one of the most demanding applications of ingenious technologies. Classification based on alphabets, numerals, special characters are the basis of various recognition systems. Artificial neural network when merged with this recognition paradigm , the system obtained is of optimum performance with minimum error .These networks constitute several neurons which are focussed at single goal which is set by the designer. This paper deals with the run through of the whole recognition system design and the various stages involved in it and neural network learning methodology.