Using Bidirectional Associative Memory Neural Networks to Solve the N-bit Task

Damiem Rolon-Mérette, Thadde Rolon-Merette, S. Chartier
{"title":"Using Bidirectional Associative Memory Neural Networks to Solve the N-bit Task","authors":"Damiem Rolon-Mérette, Thadde Rolon-Merette, S. Chartier","doi":"10.32473/flairs.36.133140","DOIUrl":null,"url":null,"abstract":"Nowadays, artificial neural networks can easily solve the N-bit parity problem. However, each time a different level must be learned, the network must be retrained. This, combined with the exponential increase of learning trials required as N grows, make these models too different from how their biological counterpart solves them. This is because humans learn to recognize patterns, count, and determine if numbers are odd or even.  Once they have learned these tasks, they can have them interact to solve any level without further training. This behavior is akin to performing multiple associations of different tasks. Therefore, it is proposed that by using bidirectional associative memory neural networks, it would be possible to solve the N-bit parity problem in a similar fashion to humans. To achieve this, two networks interacted; one served as a task Identifier and the other as a memory Extractor, giving the desired behavior influenced by the Identifier. Results showed that the model could solve the 2- to 9-bit in linear time once the associations were learned. Moreover, this was possible with 97% fewer inputs and no retraining. In addition, because of the recurrent nature of the model, it could also solve the tasks even under high noise levels.","PeriodicalId":302103,"journal":{"name":"The International FLAIRS Conference Proceedings","volume":"176 ","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The International FLAIRS Conference Proceedings","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.32473/flairs.36.133140","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Nowadays, artificial neural networks can easily solve the N-bit parity problem. However, each time a different level must be learned, the network must be retrained. This, combined with the exponential increase of learning trials required as N grows, make these models too different from how their biological counterpart solves them. This is because humans learn to recognize patterns, count, and determine if numbers are odd or even.  Once they have learned these tasks, they can have them interact to solve any level without further training. This behavior is akin to performing multiple associations of different tasks. Therefore, it is proposed that by using bidirectional associative memory neural networks, it would be possible to solve the N-bit parity problem in a similar fashion to humans. To achieve this, two networks interacted; one served as a task Identifier and the other as a memory Extractor, giving the desired behavior influenced by the Identifier. Results showed that the model could solve the 2- to 9-bit in linear time once the associations were learned. Moreover, this was possible with 97% fewer inputs and no retraining. In addition, because of the recurrent nature of the model, it could also solve the tasks even under high noise levels.
利用双向联想记忆神经网络解决n位任务
目前,人工神经网络可以很容易地解决n位奇偶校验问题。然而,每次必须学习不同的水平时,网络必须重新训练。这一点,再加上随着N的增长,所需的学习试验呈指数级增长,使得这些模型与它们的生物对应物解决问题的方式大不相同。这是因为人类学会了识别模式、计数和确定数字是奇数还是偶数。一旦他们学会了这些任务,他们就可以让他们互动解决任何关卡,而无需进一步培训。这种行为类似于执行不同任务的多个关联。因此,有人提出,通过使用双向联想记忆神经网络,有可能以类似于人类的方式解决n位奇偶校验问题。为了实现这一目标,两个网络相互作用;一个作为任务标识符,另一个作为内存提取器,给出受标识符影响的期望行为。结果表明,该模型可以在线性时间内求解出2 ~ 9位的关联。此外,这是可能的97%的投入减少,不需要再培训。此外,由于模型的循环特性,即使在高噪声水平下,它也可以解决任务。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信