An evaluation of the neocognitron

2011

This paper presents an ensemble of neo-cognitron neural network base classifiers to enhance the accuracy of the system, along the experimental results. The method offers lesser computational preprocessing in comparison to other ensemble techniques as it ex-preempts feature extraction process before feeding the data into base classifiers. This is achieved by the basic nature of neo-cognitron, it is a multilayer feed-forward neural network. Ensemble of such base classifiers gives class labels for each pattern that in turn is combined to give the final class label for that pattern. The purpose of this paper is not only to exemplify learning behavior of neocognitron as base classifiers, but also to purport better fashion to combine neural network based ensemble classifiers.

1992

Many kinds of arti cial neural networks have been applied to the recognition of handwritten characters. Fukushima's neocognitron is one of few networks that demonstrates invariance to input translation and tolerance of a signi cant degree of input distortion and deformation.

Handwritten digits recognition has been widely studied because of its potential application in automatic sorting of mail pieces. In this paper, we focus on o¤-line isolated digits with unknown scriptor. TCSF/LER has developed an intermediate approach between classical methods, based on extracting small sets of parameters, and pure neural methods, in which the network is fed with raw image data. The proposed method combines image processing and connectionnist recognition. A vector of 90 parameters consisting in pro…le curves, measures of density and morphological information is computed from the digit image. Then a multilayer perceptron trained by backpropagation is used to classify. The method has been evaluated on a huge database of real zipcodes, provided by the SRTP Nantes. The database includes around 20000 digits for learning and 12000 digits for testing. The isolated digits come from pre…lled or free envelopes. Each digit has two labels provided by two operators: the …rst one sees the whole address block and the second one is restricted to seeing only the segmented digit. In this paper, we describe our approach and we give many experimental results: recognition rates on pre…lled envelopes, on free envelopes, on digits con…rmed by the second operator, etc.

International Journal of Computing and Digital Systems

The efficiency of handwritten digit recognition models greatly relies on the classification technique used and the optimization technique involved. Motivated to explore the efficacy of machine learning for handwritten digit recognition, this study assesses the performance of three machine learning techniques, logistic regression, multilayer perceptron, and convolutional neural network for recognition of handwritten digits. The experimental results reveal that convolutional neural network outperforms logistic regression and multilayer perceptron in terms of accuracy. This study also evaluates the performance of three optimizers, namely stochastic gradient descent, adadelta, and adam for handwritten digit recognition. The experiments conducted in the study demonstrate that adam performs better than stochastic gradient descent and adadelta. It is concluded that convolutional neural network with adam is the best choice for handwritten digit recognition in terms of accuracy. However, the convolutional neural network is quite expensive in terms of training time and execution time. To this purpose, this paper proposes a methodology for the design of a lightweight convolutional neural network model.

IEE Proceedings - Vision, Image, and Signal Processing, 1996

Some modifications to an existing neural network, the neocognitron, are proposed in order to overcome some of its limitations and to achieve an improved recognition of patterns (for instance, characters). Motivation for the present work arose from the results of extensive simulation experiments on the neocognitron. Inhibition during training is dispensed with, including it only during the testing phase of the neocognitron. Even during testing, inhibition is totally discarded in the initial layer because it leads, otherwise, to some undesirable results. However, inhibition, which is feature-based, is incorporated in the later stages. The number of network parameters which are to be set manually during training is reduced. The training is made simple without involving multiple training patterns of the same nature. A new layer has been introduced after the C-layer (of the neocognitron) to scale down the network size. Finally, the response of the S-cell has been simplified, and the blurring operation between the Sand the Clayers has been changed. The new architecture, which is robust with respect to small variations in the value of the network parameters, and the associated training are believed to be simpler and more efficient than those of the neocognitron.

International Journal of Trend in Scientific Research and Development

The main objective of this paper is to recognize and predict handwritten digits from 0 to 9 where data set of 5000 examples of MNIST was given as input. As we know as every person has different style of writing digits humans can recognize easily but for co it is comparatively a difficult task so here we have used neural network approach where in the machine will learn on itself by gaining experiences and the accuracy will increase based upon the experience it gains. The dataset was trained using feed neural network algorithm. The overall system accuracy obtained was 95.7%

International Journal of Advanced Computer Science and Applications, 2018

The detection and recognition of handwritten content is the process of converting non-intelligent information such as images into machine edit-able text. This research domain has become an active research area due to vast applications in a number of fields such as handwritten filing of forms or documents in banks, exam form filled by students, users' authentication applications. Generally, the handwritten content recognition process consists of four steps: data preprocessing, segmentation, the feature extraction and selection, application of supervised learning algorithms. In this paper, a detailed survey of existing techniques used for Hand Written Digit Recognition(HWDR) is carried out. This review is novel as it is focused on HWDR and also it only discusses the application of Neural Network (NN) and its modified algorithms. We discuss an overview of NN and different algorithms which have been adopted from NN. In addition, this research study presents a detailed survey of the use of NN and its variants for digit recognition. Each existing work, we elaborate its steps, novelty, use of dataset and advantages and limitations as well. Moreover, we present a Scientometric analysis of HWDR which presents top journals and sources of research content in this research domain. We also present research challenges and potential future work.

1993

The neocognitron is an artificial neural network which applies certain aspects of the mammalian visual process to the task of 2-D pattern recognition. The resulting network model is complex in both structure and parameterization. We describe experiments which show that the performance of the neocognitron is sensitive to certain parameters whose values are seldom detailed in the relevant literature. We also present results which suggest that the selectivity parameters in the neocognitron can be adjusted in a straightforward manner so as to improve the classification performance of the neocogni tron.

Pattern Recognition, 1997

This paper presents a hierarchical neural network architecture for recognition of handwritten numeral characters. In this new architecture, two separately trained neural networks connected in series, use the pixels of the numeral image as input and yield ten outputs, the largest of which identifies the class to which the numeral image belongs. The first neural network generates the principal components of the numeral image using Oja's rule, while the second neural network uses an unsupervised learning strategy to group the principal components into distinct character clusters. In this scheme, there is more than one cluster for each numeral class. The decomposition of the global network into two independent neural networks facilitates rapid and efficient training of the individual neural networks. Results obtained with a large independently generated data set indicate the effectiveness of the proposed architecture.

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%.