Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95最新文献_第3页

Some ideas towards a grammatical model of the /spl sigma//sup 54/ bacterial promoters 对/spl sigma//sup 54/细菌启动子语法模型的一些设想

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404280

J. Collado-Vides

{"title":"Some ideas towards a grammatical model of the /spl sigma//sup 54/ bacterial promoters","authors":"J. Collado-Vides","doi":"10.1109/INBS.1995.404280","DOIUrl":"https://doi.org/10.1109/INBS.1995.404280","url":null,"abstract":"The integration of large amounts of information on the regulation of gene expression requires conceptual frameworks which should facilitate the discovery of general principles underlying different mechanisms of gene regulation. An exhaustive database of /spl sigma//sup 70/ and /spl sigma//sup 54/ promoters in E. Coli has supported the construction of a grammatical model of the /spl sigma//sup 70/ type of promoters. This grammar generates all and only those regulatory arrangements of the collection, as well as new ones which are consistent with the biological principles of the collection. In this paper, some ideas towards a unified model of the /spl sigma//sup 70/ and the /spl sigma//sup 54/ bacterial promoters are presented. This model should reflect the biological differences on the possible regulatory mechanisms of these collections. The /spl sigma//sup 54/ class represents an intermediate step between the 7/sup 0/ promoters and those present in higher organisms. Based on the biology of these bacterial promoters a hypothesis is proposed which stipulates that in principle it is feasible to activate /spl sigma//sup 70/ promoters at a distance, an exclusive property of the /spl sigma//sup 54/ class shared with promoters from higher organisms. Assuming this hypothesis is correct, some a ideas supporting a unique \"universal\" grammar for the /spl sigma//sup 70/ and /spl sigma//sup 54/ promoters are presented.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126584804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synaptically distributed memory vs. synaptically localized memory 突触分布记忆与突触局部记忆

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404271

Lipo Wang

引用次数: 0

Population dynamics in a radically epistatic genetic system 一个根本上位遗传系统中的种群动态

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404258

J. Gattiker, D. Wilson

引用次数: 1

A neocognitron synthesized by production rule for handwritten character recognition 基于生成规则合成的手写体字符识别新认知子

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404260

D. Yeung, Hing-Yip Chan, Y. C. Lau

引用次数: 2

Discovery of comprehensible symbolic rules in a neural network 神经网络中可理解符号规则的发现

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404278

Stéphane Avner

{"title":"Discovery of comprehensible symbolic rules in a neural network","authors":"Stéphane Avner","doi":"10.1109/INBS.1995.404278","DOIUrl":"https://doi.org/10.1109/INBS.1995.404278","url":null,"abstract":"In this paper, we introduce a system that extracts comprehensible symbolic rules from a multilayer perceptron. Once the network has been trained in the usual manner, the training set is presented again, and the actual activations of the units recorded. Logical rules, corresponding to the logical combinations of the incoming signals, are extracted at each activated unit. This procedure is used for all examples belonging to the training set. Thus we obtain a set of rules which account for all logical steps taken by the network to process all known input patterns. Furthermore, we show that if some symbolic meaning were associated to every input unit, then the hidden units, which have formed concepts in order to deal with recurrent features in the input data, possess some symbolic meaning tool. Our algorithm allows the recognition or the understandability of these concepts: they are found to be reducible to conjunctions and negations of the human input concepts. Our rules can also be recombined in different ways, thus constituting some limited but sound generalization of the training set. Neural networks could learn concepts about domains where little theory was known but where many examples were available. Yet, because their knowledge was stored in the synaptic strengths under numerical form, it was difficult to comprehend what they had discovered. This system therefore provides some means of accessing the information contained inside the network.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131297990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Self-organized learning in multi-layer networks 多层网络中的自组织学习

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404266

R. Brause

引用次数: 2

Generating neural networks through the induction of threshold logic unit trees 通过阈值逻辑单元树的归纳生成神经网络

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-04-25 DOI: 10.1109/INBS.1995.404272

M. Sahami

引用次数: 7