Results 1 - 10 of 35,866

Query by Committee

by H. S. Seung, M. Opper, H. Sompolinsky , 1992
"... We propose an algorithm called query by committee, in which a committee of students is trained on the same data set. The next query is chosen according to the principle of maximal disagreement. The algorithm is studied for two toy models: the high-low game and perceptron learning of another perceptr ..."
Abstract - Cited by 432 (3 self) - Add to MetaCart
perceptron. As the number of queries goes to infinity, the committee algorithm yields asymptotically finite information gain. This leads to generalization error that decreases exponentially with the number of examples. This in marked contrast to learning from randomly chosen inputs, for which the information

Reputation and Imperfect Information

by David M. Kreps, Robert Wilson - Journal of Economic Theory , 1982
"... A common observation in the informal literature of economics (and elsewhere) is that in multistage “games, ” players may seek early in the game to acquire a reputation for being “tough ” or “benevolent ” or something else. But this phenomenon is not observed in some formal game-theoretic analyses of ..."
Abstract - Cited by 519 (5 self) - Add to MetaCart
of finite games, such as Selten’s finitely repeated chain-store game or in the finitely repeated prisoners ’ dilemma. We reexamine Selten’s model, adding to it a “small ” amount of imperfect (or incomplete) information about players ’ payoffs, and we find that this addition is sufficient to give rise

Private Information Retrieval

by Benny Chor, et al.
"... We describe schemes that enable a user to access k replicated copies of a database ( k * 2) and privately retrieve informationstored in the database. This means that each individual database gets no information on the identity of the item retrieved by the user. For a single database, achieving thi ..."
Abstract - Cited by 558 (14 self) - Add to MetaCart
We describe schemes that enable a user to access k replicated copies of a database ( k * 2) and privately retrieve informationstored in the database. This means that each individual database gets no information on the identity of the item retrieved by the user. For a single database, achieving

Mediators in the architecture of future information systems

by Gio Wiederhold - IEEE COMPUTER , 1992
"... The installation of high-speed networks using optical fiber and high bandwidth messsage forwarding gateways is changing the physical capabilities of information systems. These capabilities must be complemented with corresponding software systems advances to obtain a real benefit. Without smart softw ..."
Abstract - Cited by 1135 (20 self) - Add to MetaCart
software we will gain access to more data, but not improve access to the type and quality of information needed for decision making. To develop the concepts needed for future information systems we model information processing as an interaction of data and knowledge. This model provides criteria for a high

The rate-distortion function for source coding with side information at the decoder

by Aaron D. Wyner, Jacob Ziv - IEEE Trans. Inform. Theory , 1976
"... Abstract-Let {(X,, Y,J}r = 1 be a sequence of independent drawings of a pair of dependent random variables X, Y. Let us say that X takes values in the finite set 6. It is desired to encode the sequence {X,} in blocks of length n into a binary stream*of rate R, which can in turn be decoded as a seque ..."
Abstract - Cited by 1060 (1 self) - Add to MetaCart
Abstract-Let {(X,, Y,J}r = 1 be a sequence of independent drawings of a pair of dependent random variables X, Y. Let us say that X takes values in the finite set 6. It is desired to encode the sequence {X,} in blocks of length n into a binary stream*of rate R, which can in turn be decoded as a

Graph Theory

by Reinhard Diestel , Alexander Schrijver , Paul D. Seymour - MATHEMATISCHES FORSCHUNGSINSTITUT OBERWOLFACH REPORT NO. 16/2007 , 2007
"... This week broadly targeted both finite and infinite graph theory, as well as matroids, including their interaction with other areas of pure mathematics. The talks were complemented by informal workshops focussing on specific problems or particularly active areas. ..."
Abstract - Cited by 1200 (5 self) - Add to MetaCart
This week broadly targeted both finite and infinite graph theory, as well as matroids, including their interaction with other areas of pure mathematics. The talks were complemented by informal workshops focussing on specific problems or particularly active areas.

Divergence measures based on the Shannon entropy

by Jianhua Lin - IEEE Transactions on Information theory , 1991
"... Abstract-A new class of information-theoretic divergence measures based on the Shannon entropy is introduced. Unlike the well-known Kullback divergences, the new measures do not require the condition of absolute continuity to be satisfied by the probability distributions in-volved. More importantly, ..."
Abstract - Cited by 666 (0 self) - Add to MetaCart
Abstract-A new class of information-theoretic divergence measures based on the Shannon entropy is introduced. Unlike the well-known Kullback divergences, the new measures do not require the condition of absolute continuity to be satisfied by the probability distributions in-volved. More importantly

XORs in the air: practical wireless network coding

by Sachin Katti, Hariharan Rahul, Wenjun Hu, Dina Katabi, Muriel Médard, Jon Crowcroft - In Proc. ACM SIGCOMM , 2006
"... This paper proposes COPE, a new architecture for wireless mesh networks. In addition to forwarding packets, routers mix (i.e., code) packets from different sources to increase the information content of each transmission. We show that intelligently mixing packets increases network throughput. Our de ..."
Abstract - Cited by 548 (20 self) - Add to MetaCart
This paper proposes COPE, a new architecture for wireless mesh networks. In addition to forwarding packets, routers mix (i.e., code) packets from different sources to increase the information content of each transmission. We show that intelligently mixing packets increases network throughput. Our

Cluster analysis and display of genome-wide expression patterns’,

by Michael B Eisen , Paul T Spellman , Patrick O Brown , David Botstein - Proc. Natl. Acad. , 1998
"... ABSTRACT A system of cluster analysis for genome-wide expression data from DNA microarray hybridization is described that uses standard statistical algorithms to arrange genes according to similarity in pattern of gene expression. The output is displayed graphically, conveying the clustering and th ..."
Abstract - Cited by 2895 (44 self) - Add to MetaCart
in genome-wide expression experiments can be interpreted as indications of the status of cellular processes. Also, coexpression of genes of known function with poorly characterized or novel genes may provide a simple means of gaining leads to the functions of many genes for which information

Cognitive networks

by Ryan W. Thomas, Luiz A. DaSilva, Allen B. MacKenzie - IN PROC. OF IEEE DYSPAN 2005 , 2005
"... This paper presents a definition and framework for a novel type of adaptive data network: the cognitive network. In a cognitive network, the collection of elements that make up the network observes network conditions and then, using prior knowledge gained from previous interactions with the network ..."
Abstract - Cited by 1106 (7 self) - Add to MetaCart
This paper presents a definition and framework for a novel type of adaptive data network: the cognitive network. In a cognitive network, the collection of elements that make up the network observes network conditions and then, using prior knowledge gained from previous interactions
Results 1 - 10 of 35,866