Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404259
K. Lau, S.M. Chan, L. Xu
A novel scheme, the hybrid of Lagrange and transformation approaches (Hybrid LT), was proposed by Xu (1994) to solve a combinatorial optimization problem. It separates the constraints into linear-constant-sum constraints and binary constraints. The linear-constant-sum constraints are treated by the Lagrange approach while the binary constraints are transformed into penalty or barrier functions. This paper compares the performance of the Hopfield net and the Hybrid LT based on computer simulations in solving the traveling salesman problem (TSP). The experimental results show that the Hybrid LT is superior to the Hopfield net for greater speed of convergence, higher rate of finding valid solutions and shorter paths found.<>
{"title":"Comparison of the Hopfield scheme to the hybrid of Lagrange and transformation approaches for solving the traveling salesman problem","authors":"K. Lau, S.M. Chan, L. Xu","doi":"10.1109/INBS.1995.404259","DOIUrl":"https://doi.org/10.1109/INBS.1995.404259","url":null,"abstract":"A novel scheme, the hybrid of Lagrange and transformation approaches (Hybrid LT), was proposed by Xu (1994) to solve a combinatorial optimization problem. It separates the constraints into linear-constant-sum constraints and binary constraints. The linear-constant-sum constraints are treated by the Lagrange approach while the binary constraints are transformed into penalty or barrier functions. This paper compares the performance of the Hopfield net and the Hybrid LT based on computer simulations in solving the traveling salesman problem (TSP). The experimental results show that the Hybrid LT is superior to the Hopfield net for greater speed of convergence, higher rate of finding valid solutions and shorter paths found.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"20 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":"132984911","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404264
G. Paun
Reports results concerning an extensive (ongoing) formal study of the splicing operation introduced by T. Head (1987) as a model of the recombinant behavior of DNA. The author considers the splicing with respect to finite and possibly infinite sets of rules, applied in the free mode or according to restrictions usual in language theory.<>
{"title":"The splicing as an operation on formal languages","authors":"G. Paun","doi":"10.1109/INBS.1995.404264","DOIUrl":"https://doi.org/10.1109/INBS.1995.404264","url":null,"abstract":"Reports results concerning an extensive (ongoing) formal study of the splicing operation introduced by T. Head (1987) as a model of the recombinant behavior of DNA. The author considers the splicing with respect to finite and possibly infinite sets of rules, applied in the free mode or according to restrictions usual in language theory.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"21 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":"122339996","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404270
Simon Handley
This paper shows that an evolutionary computation technique, genetic programming, can create programs that classify DNA sequences as E. coli promoter vs. non-E. coli promoter. The performance of the programs created are competitive with previous work.<>
{"title":"Predicting whether or not a nucleic acid sequence is an E. coli promoter region using genetic programming","authors":"Simon Handley","doi":"10.1109/INBS.1995.404270","DOIUrl":"https://doi.org/10.1109/INBS.1995.404270","url":null,"abstract":"This paper shows that an evolutionary computation technique, genetic programming, can create programs that classify DNA sequences as E. coli promoter vs. non-E. coli promoter. The performance of the programs created are competitive with previous work.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"38 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":"131190559","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404276
F. Achard, P. Dessen
Our goal was to study the feasibility of a system to create links between heterogeneous genomic databases. We developed a test program to build up relationships between the Genome Data Base and the Genetic Sequence Data Bank. We analyzed keywords, probes and cytogenetic locations extracted from both banks to create a network of links. The activation of the network generates new linkage data between those banks. Considering the quantity of new links created (over 50000), we could not make an exhaustive analysis of the results but the tests we performed make us think that our links are accurate. However, we also noticed that the system lacks some sensitivity, mainly due to the use of biological abbreviations or synonyms. Therefore, we propose as a conclusion some ways of enhancing the retrieval efficiency of our system.<>
{"title":"Automatic generation of links between heterogeneous genomic databases","authors":"F. Achard, P. Dessen","doi":"10.1109/INBS.1995.404276","DOIUrl":"https://doi.org/10.1109/INBS.1995.404276","url":null,"abstract":"Our goal was to study the feasibility of a system to create links between heterogeneous genomic databases. We developed a test program to build up relationships between the Genome Data Base and the Genetic Sequence Data Bank. We analyzed keywords, probes and cytogenetic locations extracted from both banks to create a network of links. The activation of the network generates new linkage data between those banks. Considering the quantity of new links created (over 50000), we could not make an exhaustive analysis of the results but the tests we performed make us think that our links are accurate. However, we also noticed that the system lacks some sensitivity, mainly due to the use of biological abbreviations or synonyms. Therefore, we propose as a conclusion some ways of enhancing the retrieval efficiency of our system.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"74 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":"123117173","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404263
Dennis Pixton
Considers closure properties of classes of languages under the operation of iterated splicing. The main result is that full abstract families of languages are closed under splicing using a regular set of splicing rules. The author has the same result for families of circular strings, with two extra assumptions: the languages in the abstract family must be closed under cyclic permutations and the splicing scheme must be reflective. In both cases the hypotheses are satisfied by the families of regular languages and of context-free languages.<>
{"title":"Linear and circular splicing systems","authors":"Dennis Pixton","doi":"10.1109/INBS.1995.404263","DOIUrl":"https://doi.org/10.1109/INBS.1995.404263","url":null,"abstract":"Considers closure properties of classes of languages under the operation of iterated splicing. The main result is that full abstract families of languages are closed under splicing using a regular set of splicing rules. The author has the same result for families of circular strings, with two extra assumptions: the languages in the abstract family must be closed under cyclic permutations and the splicing scheme must be reflective. In both cases the hypotheses are satisfied by the families of regular languages and of context-free languages.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"20 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":"124151479","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404256
Eric Rivals, J. Delahaye, M. Dauchet, O. Delgrange
The authors use Kolmogorov complexity and compression algorithms to study DOS-DNA (DOS: defined ordered sequence). This approach gives quantitative and qualitative explanations of the regularities of apparently regular regions. The authors present the problem of the coding of approximate multiple tandem repeats in order to obtain compression. Then the authors describe an algorithm that allows one to find efficiently approximate multiple tandem repeats. Finally, the authors briefly describe some of their results.<>
作者使用Kolmogorov复杂度和压缩算法来研究DOS- dna (DOS: defined ordered sequence)。这种方法对表面规则区域的规律性给出了定量和定性的解释。为了获得压缩，作者提出了近似多个串联重复序列的编码问题。然后，作者描述了一种算法，可以有效地找到近似的多个串联重复。最后，作者简要描述了他们的一些结果。
{"title":"A first step toward chromosome analysis by compression algorithms","authors":"Eric Rivals, J. Delahaye, M. Dauchet, O. Delgrange","doi":"10.1109/INBS.1995.404256","DOIUrl":"https://doi.org/10.1109/INBS.1995.404256","url":null,"abstract":"The authors use Kolmogorov complexity and compression algorithms to study DOS-DNA (DOS: defined ordered sequence). This approach gives quantitative and qualitative explanations of the regularities of apparently regular regions. The authors present the problem of the coding of approximate multiple tandem repeats in order to obtain compression. Then the authors describe an algorithm that allows one to find efficiently approximate multiple tandem repeats. Finally, the authors briefly describe some of their results.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"1 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":"131192962","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404255
R. Reynolds, S. R. Rolnick
There are two basic approaches to image segmentation, region-based and neighborhood-based. Region-based approaches require less a priori knowledge about the scene than neighborhood-based approaches but are computationally more expensive. In cases where there is little prior knowledge about properties of the image, one is often forced to use region growing approaches. In this paper the authors use cultural algorithms, a form of evolutionary computation based upon principles of cultural evolution, as the basis for learning the parameters for a neighborhood-based approach to image segmentation from the results of a region-growing approach. Specifically, parameters for a differential gradient method utilizing the Sobel operator are learned from the results of a region growing approach. The prototype is applied to a sequence of real world images, taken from archaeological excavations of a prehistoric site in order to extract spatial activity areas in the site. A region-growing approach is applied first to the images, and then a cultural algorithm is used to extract the parameters for use by a gradient method for those images. The resulting performance of the gradient method produced a correspondence of over 95% with that of the original.<>
{"title":"Learning the parameters for a gradient-based approach to image segmentation using cultural algorithms","authors":"R. Reynolds, S. R. Rolnick","doi":"10.1109/INBS.1995.404255","DOIUrl":"https://doi.org/10.1109/INBS.1995.404255","url":null,"abstract":"There are two basic approaches to image segmentation, region-based and neighborhood-based. Region-based approaches require less a priori knowledge about the scene than neighborhood-based approaches but are computationally more expensive. In cases where there is little prior knowledge about properties of the image, one is often forced to use region growing approaches. In this paper the authors use cultural algorithms, a form of evolutionary computation based upon principles of cultural evolution, as the basis for learning the parameters for a neighborhood-based approach to image segmentation from the results of a region-growing approach. Specifically, parameters for a differential gradient method utilizing the Sobel operator are learned from the results of a region growing approach. The prototype is applied to a sequence of real world images, taken from archaeological excavations of a prehistoric site in order to extract spatial activity areas in the site. A region-growing approach is applied first to the images, and then a cultural algorithm is used to extract the parameters for use by a gradient method for those images. The resulting performance of the gradient method produced a correspondence of over 95% with that of the original.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"44 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":"122674994","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404283
N. Ishii, K. Naka
Asymmetrical neural networks are shown in a biological neural network, the catfish retina. Several mechanisms have been proposed for the detection of motion in biological system. Hassenstein and Reichardt network (1956) and Barlow and Levick network (1965) of movements are similar to the asymmetrical network developed here. To make clear the difference among these asymmetrical networks, we applied nonlinear analysis developed by N. Wiener. Then, we can derive the /spl alpha/-equation of movement, which shows the direction of movement. During the movement, we also can derive the movement equation, which implies that the movement holds regardless of the parameter /spl alpha/. By analyzing the biological asymmetric neural networks, it is shown that the asymmetric networks are excellent in the ability of spatial information processing on the retinal level. The symmetric network was discussed by applying nonlinear analysis. In the symmetric neural network, it was suggested that memory function is needed to perceive the movement.<>
{"title":"Movement and memory function in biological neural networks","authors":"N. Ishii, K. Naka","doi":"10.1109/INBS.1995.404283","DOIUrl":"https://doi.org/10.1109/INBS.1995.404283","url":null,"abstract":"Asymmetrical neural networks are shown in a biological neural network, the catfish retina. Several mechanisms have been proposed for the detection of motion in biological system. Hassenstein and Reichardt network (1956) and Barlow and Levick network (1965) of movements are similar to the asymmetrical network developed here. To make clear the difference among these asymmetrical networks, we applied nonlinear analysis developed by N. Wiener. Then, we can derive the /spl alpha/-equation of movement, which shows the direction of movement. During the movement, we also can derive the movement equation, which implies that the movement holds regardless of the parameter /spl alpha/. By analyzing the biological asymmetric neural networks, it is shown that the asymmetric networks are excellent in the ability of spatial information processing on the retinal level. The symmetric network was discussed by applying nonlinear analysis. In the symmetric neural network, it was suggested that memory function is needed to perceive the movement.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"7 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":"128519318","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404267
W. Stark, J. Pedersen
The grand challenge of distributed processes is to bridge the chasm separating local...from global.... How does cellular behavior determine structure and behavior at the tissue level? How do the switching characteristics of transistors determine the behavior of a computer chip? The first of these questions is made difficult by the amorphous nature of communication between components. In both theory and simulations, the authors use large irregular networks of automata with asynchronous activity as models. The local structure is seen in the automaton's state-transition diagram. The global structure is seen in the global computation space. THEME: In entropy-reducing processes, the global attractors are homomorphic to the local slate-transition graph. The authors' investigations focus on systems of oscillators, on Turing's leopards' spot problem, and on networks of finite state automata. To the extent that global structure corresponds to global behavior, the authors' results provide a way of reducing the behavior of a tissue to that of its cells (a fundamental problem of biology).<>
{"title":"Mathematics for a fundamental problem of biological information processing","authors":"W. Stark, J. Pedersen","doi":"10.1109/INBS.1995.404267","DOIUrl":"https://doi.org/10.1109/INBS.1995.404267","url":null,"abstract":"The grand challenge of distributed processes is to bridge the chasm separating local...from global.... How does cellular behavior determine structure and behavior at the tissue level? How do the switching characteristics of transistors determine the behavior of a computer chip? The first of these questions is made difficult by the amorphous nature of communication between components. In both theory and simulations, the authors use large irregular networks of automata with asynchronous activity as models. The local structure is seen in the automaton's state-transition diagram. The global structure is seen in the global computation space. THEME: In entropy-reducing processes, the global attractors are homomorphic to the local slate-transition graph. The authors' investigations focus on systems of oscillators, on Turing's leopards' spot problem, and on networks of finite state automata. To the extent that global structure corresponds to global behavior, the authors' results provide a way of reducing the behavior of a tissue to that of its cells (a fundamental problem of biology).<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"80 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":"126195700","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}
Pub Date : 1995-05-29DOI: 10.1109/INBS.1995.404279
J. Paredis
Discusses various avenues for exploiting biological learning mechanisms within machine learning. Special attention is given to the following issues: (a) the reasons for the wide variety of biological learning mechanisms; (b) the relation between lifetime and genetic learning; (c) a description of the driving forces of genetic learning and their use in evolutionary computation. Various symbolic machine learning and reasoning techniques can be used to complement (genetic and/or neural) sub-symbolic learning. A first approach uses symbolic induction for explaining the behavior of (genetically evolved) neural nets. Next, a general framework for the use of (symbolic) domain knowledge during genetic learning is introduced.<>
{"title":"Learning at the crossroads of biology and computation","authors":"J. Paredis","doi":"10.1109/INBS.1995.404279","DOIUrl":"https://doi.org/10.1109/INBS.1995.404279","url":null,"abstract":"Discusses various avenues for exploiting biological learning mechanisms within machine learning. Special attention is given to the following issues: (a) the reasons for the wide variety of biological learning mechanisms; (b) the relation between lifetime and genetic learning; (c) a description of the driving forces of genetic learning and their use in evolutionary computation. Various symbolic machine learning and reasoning techniques can be used to complement (genetic and/or neural) sub-symbolic learning. A first approach uses symbolic induction for explaining the behavior of (genetically evolved) neural nets. Next, a general framework for the use of (symbolic) domain knowledge during genetic learning is introduced.<<ETX>>","PeriodicalId":423954,"journal":{"name":"Proceedings First International Symposium on Intelligence in Neural and Biological Systems. INBS'95","volume":"55 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":"132436237","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：