{"title":"Multiterminal estimation theory","authors":"T. Han, S. Amari","doi":"10.1109/ITW.1989.761411","DOIUrl":"https://doi.org/10.1109/ITW.1989.761411","url":null,"abstract":"The basic questions here are how to construct effective encoders @,Q2 and the related estimators 6 for the parameter 0; what is the minimum variance of these estimators ?; and what is the maximum Fisher information attainable under the rate constraints RI .R2 for the Shannon information ?. etc. We shall give several substantial answers to these problems which include as special cases the previous results by Zhang and Berger, and by Ahlswede and Burnashev. The present results have been established technically on the basis of universal coding for relevant auxiliary random variables, projection operation for multivariate Gaussian statistics, introduction of a dual pair of orthogonal coordinate systems, and also geometry of Kullback-Leibler's divergences, etc. Such an approach is essentially along the differential-geometrical standpoint provided by Amari in studying the zero-rate estimators. Our estimators can be regarded as a kind of the generalized maximum-likelihood estimators of invariant form under parameter transformations, and are very naturally extended to the multi-parameter case, in contrast with those previously known estimators. As a by-product, we shall show a simple new proof to the result by Zhang and Berger, which enables us to have a clearer understanding for the additivity condition assumed by them.","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124408851","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}
{"title":"Trellis Constrained Run Length Codes","authors":"M. Belongie, C. Heegard","doi":"10.1109/ITW.1989.761429","DOIUrl":"https://doi.org/10.1109/ITW.1989.761429","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116853979","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}
{"title":"Upper and Lower Expectations","authors":"Amir Sadrolhefazi, T. Fine","doi":"10.1109/ITW.1989.761419","DOIUrl":"https://doi.org/10.1109/ITW.1989.761419","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131728286","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}
{"title":"Computer algebra constructions of geometric codes","authors":"M. Hassner","doi":"10.1109/ITW.1989.761399","DOIUrl":"https://doi.org/10.1109/ITW.1989.761399","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133085514","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}
{"title":"Polynomial Threshold Elements?","authors":"Jehoshua Bruck","doi":"10.1109/ITW.1989.761437","DOIUrl":"https://doi.org/10.1109/ITW.1989.761437","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114237108","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}
{"title":"An Information Theoretic Approach to Modeling Neural Network Expert Systems","authors":"R. Goodman, J. W. Miller, Padhraic Smyth","doi":"10.1109/ITW.1989.761436","DOIUrl":"https://doi.org/10.1109/ITW.1989.761436","url":null,"abstract":"In this paper we propose several novel techniques for mapping rule bases, such as are used in rule based expert systems, onto neural network architectures. Our objective in doing this is to achieve a system capable of incremental learning, and distributed probabilistic inference. Such a system would be capable of performing inference many orders of magnitude faster than current serial rule based expert systems, and hence be capable of true real time operation. In addition, the rule based formalism gives the system an explicit knowledge representation, unlike current neural models. We propose an information-theoretic approach to this problem, which really has two aspects: firstly learning the model and, secondly, performing inference using this model. We will show a clear pathway to implementing an expert system starting from raw data, via a learned rule-based model, to a neural network that performs distributed inference.","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"139 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125824168","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}
{"title":"Constructions of (d, k) Codes","authors":"L. Frederickson","doi":"10.1109/ITW.1989.761427","DOIUrl":"https://doi.org/10.1109/ITW.1989.761427","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130178401","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}
{"title":"Channels with ISI Memory: Information-Theoretical Properties and Applications to Digital Magnetic Recording","authors":"W. Hirt","doi":"10.1109/ITW.1989.761424","DOIUrl":"https://doi.org/10.1109/ITW.1989.761424","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124546054","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}
{"title":"Summary of decoding algebraic geometry codes","authors":"S. C. Porter","doi":"10.1109/ITW.1989.761398","DOIUrl":"https://doi.org/10.1109/ITW.1989.761398","url":null,"abstract":"P - QS = 0 mod g. 3) Evaluate the residues of Gdz. For non-zero genus the same general program is possible, but enormous difficulties must be overcome. The first step is the description of a new finite data structure for the affine coordinate ring, permitting efficient arithmetic algorithms. To define the data structure, existence of a non-singular affine embedding with one point at infinity must be proved. . Syndrome construction and conversion of the decoding problem to a polynomial congruence is made possible by the definition of a polynomial whose divisor of zeros is exactly G and by the construction of a space of differentials which corresponds to F; and contains Q(G - D). Euclid’s algorithm is generalized for non-Euclidean affine coordinate rings. First, a generalized resultant matrix is defined. By selecting pivots in a certain order during row-reduction on the resultant matrix, objects much like remainders and convergents occur. It is proved that these objects provide minimal solutions to the polynomial congruence. 0 mod G need not be a minimal solution of 5 - S 3 0 mod G. The % error loss stems from this. Further degradation of decoding capacity occurs for some choices of the curve X, the point P, and the divisor S. The algorithm consists of efficient, easily implemented matrix operations. However, the algebraic geometry and approximation techniques necessary to develop and understand the method are both original and deep. errors in genus p.","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122781719","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}
{"title":"Collective Oscillations and Coherent Patterns in Neural Networks Models","authors":"P. Baldi","doi":"10.1109/ITW.1989.761440","DOIUrl":"https://doi.org/10.1109/ITW.1989.761440","url":null,"abstract":"","PeriodicalId":413028,"journal":{"name":"IEEE/CAM Information Theory Workshop at Cornell","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121018998","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}