首页> 外文期刊>Neural computation >Storing Object-Dependent Sparse Codes in aWillshaw Associative Network
【24h】

Storing Object-Dependent Sparse Codes in aWillshaw Associative Network

机译:在Willshaw关联网络中存储对象相关的稀疏代码

获取原文
获取原文并翻译 | 示例

摘要

Willshaw networks are single-layered neural networks that store associations between binary vectors. Using only binary weights, these networks can be implemented efficiently to store large numbers of patterns and allow for fault-tolerant recovery of those patterns from noisy cues. However, this is only the case when the involved codes are sparse and randomly generated. In this letter, we use a recently proposed approach that maps visual patterns into informative binary features. By doing so, we manage to transformMNIST handwritten digits into well-distributed codes that we then store in a Willshaw network in autoassociation. We perform experiments with both noisy and noiseless cues and verify a tenuous impact on the recovered pattern’s relevant information. More specifically, we were able to perform retrieval after filling the memory to several factors of its number of units while preserving the information of the class to which the pattern belongs.
机译:Willshaw网络是单层神经网络,用于存储二进制向量之间的关联。仅使用二进制权重,就可以有效地实现这些网络,以存储大量模式,并允许从噪声提示中容错恢复这些模式。但是,仅当所涉及的代码稀疏且随机生成时,才是这种情况。在这封信中,我们使用了一种最近提出的方法,该方法将视觉模式映射为信息丰富的二进制特征。这样,我们设法将MNIST手写数字转换为分布良好的代码,然后以自动关联的方式存储在Willshaw网络中。我们以嘈杂和无声的提示进行实验,并验证了对恢复模式相关信息的微弱影响。更具体地说,我们可以在将内存填充到其单位数量的几个因素之后执行检索,同时保留模式所属的类的信息。

著录项

  • 来源
    《Neural computation》 |2020年第1期|136-152|共17页
  • 作者

    Luis Sa-Couto; AndreasWichert;

  • 作者单位

    Department of Computer Science and Engineering INESC-ID & Instituto Superior Tecnico University of Lisbon 2744-016 Porto Salvo Portugal;

  • 收录信息 美国《科学引文索引》(SCI);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号