Classification of Handwritten Digits using a RAM Neural Net Architecture

Author:

Jørgensen Thomas Martini1

Affiliation:

1. Optics & Fluid Dynamics Department, Risø National Laboratory, P.O. Box 49, DK-4000 Roskilde, Denmark

Abstract

Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Networks and Communications,General Medicine

Reference4 articles.

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Logic-Based Neural Network for Pattern Correction;2022 International Conference on Smart Systems and Power Management (IC2SPM);2022-11-10

2. Weightless Neural Models: An Overview;Women in Computational Intelligence;2022

3. A massively parallel pipelined reconfigurable design for M-PLN based neural networks for efficient image classification;Neurocomputing;2016-03

4. A novel neuro-fuzzy classifier based on weightless neural network;Proceedings of the International Conference and Workshop on Emerging Trends in Technology;2010-02-26

5. On a hybrid weightless neural system;International Journal of Bio-Inspired Computation;2009

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3