CiteSeerX — Search Results

Results 1 - 10 of 8,930

Solving multiclass learning problems via error-correcting output codes

by Thomas G. Dietterich, Ghulum Bakiri - JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH , 1995

"... Multiclass learning problems involve nding a de nition for an unknown function f(x) whose range is a discrete set containing k>2values (i.e., k \classes"). The de nition is acquired by studying collections of training examples of the form hx i;f(x i)i. Existing approaches to multiclass l ..."

Abstract - Cited by 726 (8 self) - Add to MetaCart

output representations. This paper compares these three approaches to a new technique in which error-correcting codes are employed as a distributed output representation. We show that these output representations improve the generalization performance of both C4.5 and backpropagation on a wide range

What output size resists collisions in

by Daniel J. Bernstein

"... a xor of independent expansions? ..."

Abstract - Add to MetaCart

a xor of independent expansions?

Optimizing PDF output size of TEX documents

by unknown authors

"... There are several tools for generating PDF output from a TEX document. By choosing the appropriate tools and configuring them properly, it is possible to reduce the PDF output size by a factor of 3 or even more, thus reducing document download times, hosting and archiving costs. We enumerate the mos ..."

Abstract - Add to MetaCart

There are several tools for generating PDF output from a TEX document. By choosing the appropriate tools and configuring them properly, it is possible to reduce the PDF output size by a factor of 3 or even more, thus reducing document download times, hosting and archiving costs. We enumerate

Optimizing PDF output size of TEX documents

by Péter Szabó

Abstract - Add to MetaCart

Optimizing PDF output size of TEX documents

by unknown authors

Abstract - Add to MetaCart

Multivariable Feedback Control: Analysis

by Sigurd Skogestad, Ian Postlethwaite - span (B∗) und Basis B∗ = { ω1 , 2005

"... multi-input, multi-output feed-back control design for linear systems using the paradigms, theory, and tools of robust con-trol that have arisen during the past two decades. The book is aimed at graduate students and practicing engineers who have a basic knowledge of classical con-trol design and st ..."

Abstract - Cited by 564 (24 self) - Add to MetaCart

multi-input, multi-output feed-back control design for linear systems using the paradigms, theory, and tools of robust con-trol that have arisen during the past two decades. The book is aimed at graduate students and practicing engineers who have a basic knowledge of classical con-trol design

Raptor codes

by Amin Shokrollahi - IEEE Transactions on Information Theory , 2006

"... LT-Codes are a new class of codes introduced in [1] for the purpose of scalable and fault-tolerant distribution of data over computer networks. In this paper we introduce Raptor Codes, an extension of LT-Codes with linear time encoding and decoding. We will exhibit a class of universal Raptor codes: ..."

Abstract - Cited by 577 (7 self) - Add to MetaCart

: for a given integer k, and any real ε> 0, Raptor codes in this class produce a potentially infinite stream of symbols such that any subset of symbols of size k(1 + ε) is sufficient to recover the original k symbols with high probability. Each output symbol is generated using O(log(1/ε)) operations

The cascade-correlation learning architecture

by Scott E. Fahlman, Christian Lebiere - Advances in Neural Information Processing Systems 2 , 1990

"... Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creatin ..."

Abstract - Cited by 801 (6 self) - Add to MetaCart

, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade

Iterative decoding of binary block and convolutional codes

by Joachim Hagenauer, Elke Offer, Lutz Papke - IEEE TRANS. INFORM. THEORY , 1996

"... Iterative decoding of two-dimensional systematic convolutional codes has been termed “turbo” (de)coding. Using log-likelihood algebra, we show that any decoder can he used which accepts soft inputs-including a priori values-and delivers soft outputs that can he split into three terms: the soft chann ..."

Abstract - Cited by 610 (43 self) - Add to MetaCart

Iterative decoding of two-dimensional systematic convolutional codes has been termed “turbo” (de)coding. Using log-likelihood algebra, we show that any decoder can he used which accepts soft inputs-including a priori values-and delivers soft outputs that can he split into three terms: the soft

Graphcut textures: Image and video synthesis using graph cuts

by Vivek Kwatra, Arno Schödl, Irfan Essa, Greg Turk, Aaron Bobick - ACM Transactions on Graphics, SIGGRAPH 2003 , 2003

"... This banner was generated by merging the source images in Figure 6 using our interactive texture merging technique. In this paper we introduce a new algorithm for image and video texture synthesis. In our approach, patch regions from a sample image or video are transformed and copied to the output a ..."

Abstract - Cited by 490 (9 self) - Add to MetaCart

and then stitched together along optimal seams to generate a new (and typically larger) output. In contrast to other techniques, the size of the patch is not chosen a-priori, but instead a graph cut technique is used to determine the optimal patch region for any given offset between the input and output texture

Results 1 - 10 of 8,930

Tools