Modeling Efficient Conjunction Detection with Spiking Neural Networks.pdfVIP

下载本文档

0
0
约1.66万字
约 7页
2017-04-13 发布于江苏
举报
版权申诉

Modeling Efficient Conjunction Detection with Spiking Neural Networks.pdf

1、有哪些信誉好的足球投注网站（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Modeling Efficient Conjunction Detection with Spiking Neural Networks

MODELING EFFICIENT CONJUNCTION DETECTION WITH SPIKING NEURAL NETWORKS This re-print corresponds to the paper “Modeling Efficient Con- junction Detection with Spiking Neural Networks”, by Sander M. Bohte, Joost N. Kok, and Han La Poutre?, and is to appear in the Proceedings of the European Symposium on Artificial Neural Networks ESANN’2002, Bruge, Belgium, 2002. Modeling Efficient Conjunction Detection with Spiking Neural Networks Sander M. Bohte1, Joost N. Kok1,2 and Han La Poutre?1,3 1CWI, Kruislaan 413, 1090 GB Amsterdam, P.O. Box 94079, The Netherlands 2LIACS, Leiden University, 2300 RA Leiden, P.O. Box 9512, The Netherlands 3STM, Eindhoven University of Technology, The Netherlands Abstract. The design of neural networks that are able to efficiently encode and detect conjunctions of features is an important open challenge that is also referred to as “the binding-problem”. We define a formal framework for neural nodes that process activity in the form of tuples of spike-trains which can efficiently encode and detect feature-conjunctions on a retinal input field in a position-invariant manner, also in the presence of multiple feature-conjunctions. 1 Introduction The representation of structured information in neural networks has so far not been satisfactory solved, though it is thought to be required for efficiently solv- ing a number of notoriously hard problems [1]. In a linguistic sentence like The red apple and the green pear, grammar implies the structuring of elements “red”, “green”, “apple”, and “pear” into semantic composites, in brackets: {{red,apple}, {green,pear}}. The binding-problem refers to the problem of how to encode and detect such structured representations in neural networks. Whereas we can identify elements like red, green, apple, and pear each with a correspond- ing (active) neuron, the embodiment of the structural brackets has been much debated, as far back as Hebb, in 1949. Some have even argued that structural representation is impossible i