Journal ArticleDOI
Multilayer cluster neural network for totally unconstrained handwritten numeral recognition
Reads0
Chats0
TLDR
In this article, a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals was proposed, and the use of genetic algorithms for avoiding the problem of finding local minima in training the multi-layer cluster neural networks with gradient descent technique reduces error rates.About:
This article is published in Neural Networks.The article was published on 1995-10-01. It has received 68 citations till now. The article focuses on the topics: Artificial neural network.read more
Citations
More filters
Journal ArticleDOI
Handwritten digit recognition: benchmarking of state-of-the-art techniques
TL;DR: The results of handwritten digit recognition on well-known image databases using state-of-the-art feature extraction and classification techniques are competitive to the best ones previously reported on the same databases.
Journal ArticleDOI
Handwritten digit recognition: investigation of normalization and feature extraction techniques
TL;DR: A comparison of normalization functions shows that moment-based functions outperform the dimension-based ones and the aspect ratio mapping is influential and the comparison of feature vectors shows that the improved feature extraction strategies outperform their baseline counterparts.
Journal ArticleDOI
An efficient method to construct a radial basis function neural network classifier
Young-Sup Hwang,Sung-Yang Bang +1 more
TL;DR: A method to construct an RBFN classifier efficiently and effectively is described that determines the middle layer neurons by a fast clustering algorithm and computes the optimal weights between the middle and the output layers statistically.
Journal ArticleDOI
Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition
Cheng-Lin Liu,Masaki Nakagawa +1 more
TL;DR: In this paper, prototype learning is used to improve the classification performance of nearest-neighbor (NN) classifier and reduce the storage and computation requirements of NN classifier.
Journal ArticleDOI
Modularity in neural computing
Terry Caelli,Ling Guan,W. Wen +2 more
TL;DR: It is argued that this modular approach to neural computing is more in line with the neurophysiology of the vertebrate cerebral cortex, particularly with respect to sensation and perception, and has the potential to aid in solutions to large-scale network computational problems.
References
More filters
Book
Adaptation in natural and artificial systems
TL;DR: Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.
Book
Learning internal representations by error propagation
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Journal ArticleDOI
Neocognitron: A Hierarchical Neural Network Capable of Visual Pattern Recognition
TL;DR: The operation of tolerating positional error a little at a time at each stage, rather than all in one step, plays an important role in endowing the network with an ability to recognize even distorted patterns.