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

Modeling sensory representations in brain: new methods for studying functional architecture reveal unique spatial patterns 大脑感官表征建模:研究功能建筑的新方法揭示了独特的空间模式

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404290

D.R. Roberts, C. Koutsougeras, R. Nudo, C. Cusick

引用次数: 0

Knowledge-based simulation of regulatory action in lambda phage 基于知识的lambda噬菌体调节作用模拟

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404274

T. Shimada, M. Hagiya, M. Arita, S. Nishizaki, C. Tan

引用次数: 11

DNA evolutionary linguistics and RNA structure modeling: a computational approach DNA进化语言学和RNA结构建模:一种计算方法

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404281

T. Yokomori, S. Kobayashi

{"title":"DNA evolutionary linguistics and RNA structure modeling: a computational approach","authors":"T. Yokomori, S. Kobayashi","doi":"10.1109/INBS.1995.404281","DOIUrl":"https://doi.org/10.1109/INBS.1995.404281","url":null,"abstract":"The authors are concerned with analysing formal linguistic properties of DNA sequences in which a number of the language theoretic analysis on DNA sequences are established by means of computational methods. First, employing a formal language theoretic framework, the authors consider a kind of evolutionary problem of DNA sequences, asking (1) how DNA sequences were initially created and then evolved (grew up) to be a language of certain complexity, and (2) what primitive constructs were minimally required for the process of evolution. In terms of formal linguistic concepts, the authors present several results that provide their views on these questions at a conceptual level. Based on the formal analysis on these biological questions, the authors then choose a certain type of tree generating grammars called tree adjunct grammars (TAG) to attach the problem of modeling the secondary structure of RNA sequences. By proposing an extended model of TAGs, the authors demonstrate the usefulness of the grammars for modeling some typical RNA secondary structures including \"pseudoknots\", which suggests that TAG families as RNA grammars have a great potential for RNA secondary structure prediction.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"54 11 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":"132714045","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: 29

KYDON, a self-organized autonomous net: learning model and failure recovery 自组织自治网络KYDON:学习模型与故障恢复

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404265

J. S. Mertoguno, G. Bourbakis

引用次数: 2

Drosophila GRAIL: an intelligent system for gene recognition in Drosophila DNA sequences 果蝇GRAIL:果蝇DNA序列基因识别的智能系统

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404269

Ying Xu, G. Helt, J. Einstein, G. Rubin, E. Uberbacher

{"title":"Drosophila GRAIL: an intelligent system for gene recognition in Drosophila DNA sequences","authors":"Ying Xu, G. Helt, J. Einstein, G. Rubin, E. Uberbacher","doi":"10.1109/INBS.1995.404269","DOIUrl":"https://doi.org/10.1109/INBS.1995.404269","url":null,"abstract":"An AI-based system for gene recognition in Drosophila DNA sequences was designed and implemented. The system consists of two main modules, one for coding exon recognition and one for single gene model construction. The exon recognition module finds a coding exon by recognition of its splice junctions (or translation start) and coding potential. The core of this module is a set of neural networks which evaluate an exon candidate for the possibility of being a true coding exon using the \"recognized\" splice junction (or translation start) and coding signals. The recognition process consists of four steps: generation of an exon candidate pool, elimination of improbable candidates using heuristic rules, candidate evaluation by trained neural networks, and candidate cluster resolution and final exon prediction. The gene model construction module takes as input the clustered exon candidates and builds a \"best\" possible single gene model using an efficient dynamic programming algorithm. 129 Drosophila sequences consisting of 441 coding exons including 216358 coding bases were extracted from GenBank and used to build statistical matrices and to train the neural networks. On this training set the system recognized 97% of the coding messages and predicted only 5% false messages. Among the \"correctly\" predicted exons, 68% match the actual exon exactly and 96% have at least one edge predicted correctly. On an independent test set consisting of 30 Drosophila sequences, the system recognized 96% of the coding messages and predicted 7% false messages.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"95 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":"126144593","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: 6

Gene classification artificial neural system 基因分类人工神经系统

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404273

Cathy H. Wu, Hsi-Lien Chen, Sheng-Chih Chen

{"title":"Gene classification artificial neural system","authors":"Cathy H. Wu, Hsi-Lien Chen, Sheng-Chih Chen","doi":"10.1109/INBS.1995.404273","DOIUrl":"https://doi.org/10.1109/INBS.1995.404273","url":null,"abstract":"A gene classification artificial neural system has been developed for rapid annotation of the molecular sequencing data being generated by the Human Genome Project. Three neural networks have been implemented, one full-scale system to classify protein sequences according to PIR (protein identification resources) superfamilies, one system to classify ribosomal RNA sequences into RDP (ribosomal database project) phylogenetic classes, and one pilot system to classify proteins according to Blocks motifs. The sequence encoding schema involved an n-gram hashing method to convert molecular sequences into neural input vectors, a SVD (singular value decomposition) method to compress vectors, and a term weighting method to extract motif information. The neural networks used were three-layered, feed-forward networks that employed backpropagation or counter-propagation learning paradigms. The system runs faster by one to two orders of magnitude than existing method and has a sensitivity of 85 to 100%. The gene classification artificial neural system is available on the Internet, and may be extended into a gene identification system for classifying indiscriminately sequenced DNA fragments.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"30 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":"114581263","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: 32

A genetic algorithm for decomposition type choice in OKFDDs okfdd分解类型选择的遗传算法

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404257

R. Drechsler, B. Becker, Nicole Drechsler, A. Jahnke

引用次数: 3

A neural network model of the cortico-hippocampal interplay: contexts and generalization 皮质-海马相互作用的神经网络模型:背景和概括

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404282

A. Bibbig, T. Wennekers, G. Palm

{"title":"A neural network model of the cortico-hippocampal interplay: contexts and generalization","authors":"A. Bibbig, T. Wennekers, G. Palm","doi":"10.1109/INBS.1995.404282","DOIUrl":"https://doi.org/10.1109/INBS.1995.404282","url":null,"abstract":"We present computer simulations of a neural network comprising two sensory pathways, each built of preprocessing and associative memory modules perhaps corresponding to a primary and higher sensory area, and a hippocampal area that serves as an integration or fusion zone during learning and retrieval of polymodal information. The network is able to store unimodal details about a complex environment in local assemblies restricted to the corresponding associative memory, whereas a representation of the simultaneous occurrences of several stimuli is constituted and stored in a self-organizing manner in the hippocampal area. This can be viewed as storage of a \"particular context\". If many stimulus constellations are presented to the network during learning, it may over-learn, that is, the hippocampal area can no longer distinguish particular situations, but instead represents more general contexts or categories, a given environmental situation may belong to. Feedback from the hippocampal region to association areas can restore particular memories; it can still act as a threshold control gate raising sensitivity in the appropriate cortex regions when it is overloaded.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"36 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":"130124381","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: 4

Hybrid nets with variable parameters: a novel approach to fast learning under backpropagation 变参数混合网络:一种反向传播下快速学习的新方法

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404277

Jun Han, C. Moraga

引用次数: 2

A new model for the cognitive process. Artificial cognition 认知过程的新模型。人工识别

Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95 Pub Date : 1995-05-29 DOI: 10.1109/INBS.1995.404261

R. Keene

引用次数: 0