Deep Convolutional Self-Organizing Map Network for Robust Handwritten Digit Recognition
نویسندگان
چکیده
منابع مشابه
Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM)
The adaptive-subspace self-organizing map (ASSOM) proposed by Kohonen is a recent development in self-organizing map (SOM) computation. In this paper, we propose a method to realize ASSOM using a neural learning algorithm in nonlinear autoencoder networks. Our method has the advantage of numerical stability. We have applied our ASSOM model to build a modular classification system for handwritte...
متن کاملPersian Handwritten Digit Recognition Using Particle Swarm Probabilistic Neural Network
Handwritten digit recognition can be categorized as a classification problem. Probabilistic Neural Network (PNN) is one of the most effective and useful classifiers, which works based on Bayesian rule. In this paper, in order to recognize Persian (Farsi) handwritten digit recognition, a combination of intelligent clustering method and PNN has been utilized. Hoda database, which includes 80000 P...
متن کاملApplication of Growing Hierarchical Self-Organizing Map in Handwritten Digit Recognition
This paper discusses the application of a GH-SOM architecture to the problem of Handwritten Digit Recognition. The results proved to be better than the ones obtained from standard SOM networks.
متن کاملAdaptive Offset Subspace Self-Organizing Map: An Application to Handwritten Digit Recognition?
An Adaptive-Subspace Self-Organizing Map (ASSOM) can learn a set of ordered linear subspaces which correspond to invariant classes. However the basic ASSOM cannot properly learn linear manifolds that are shifted away from the origin of the input space. In this paper, we propose an improvement on ASSOM to amend this deficiency. The new network, named AOSSOM for Adaptive Offset Subspace Self-Orga...
متن کاملDeep Convolutional Network for Handwritten Chinese Character Recognition
In this project we explored the performance of deep convolutional neural network on recognizing handwritten Chinese characters. We ran experiments on a 200-class and a 3755-class dataset using convolutional networks with different depth and filter numbers. Experimental results show that deeper network with larger filter numbers give better test accuracy. We also provide a visualization of the l...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2020
ISSN: 2169-3536
DOI: 10.1109/access.2020.3000829