Results 1  10
of
1,185
Exploiting Generative Models in Discriminative Classifiers
 In Advances in Neural Information Processing Systems 11
, 1998
"... Generative probability models such as hidden Markov models provide a principled way of treating missing information and dealing with variable length sequences. On the other hand, discriminative methods such as support vector machines enable us to construct flexible decision boundaries and often resu ..."
Abstract

Cited by 551 (9 self)
 Add to MetaCart
result in classification performance superior to that of the model based approaches. An ideal classifier should combine these two complementary approaches. In this paper, we develop a natural way of achieving this combination by deriving kernel functions for use in discriminative methods such as support
Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations
, 2005
"... How do real graphs evolve over time? What are “normal” growth patterns in social, technological, and information networks? Many studies have discovered patterns in static graphs, identifying properties in a single snapshot of a large network, or in a very small number of snapshots; these include hea ..."
Abstract

Cited by 541 (48 self)
 Add to MetaCart
increase slowly as a function of the number of nodes (like O(log n) orO(log(log n)). Existing graph generation models do not exhibit these types of behavior, even at a qualitative level. We provide a new graph generator, based on a “forest fire” spreading process, that has a simple, intuitive justification
Likelihoodbased belief function: justification and some extensions to lowquality data
"... Given a parametric statistical model, evidential methods of statistical inference aim at constructing a belief function on the parameter space from observations. The two main approaches are Dempster’s method, which regards the observed variable as a function of the parameter and an auxiliary varia ..."
Abstract
 Add to MetaCart
Given a parametric statistical model, evidential methods of statistical inference aim at constructing a belief function on the parameter space from observations. The two main approaches are Dempster’s method, which regards the observed variable as a function of the parameter and an auxiliary
Justification
, 1993
"... The purpose of this thesis wan to develop a set of control laws, impleme~nted in a simulation, to allow the Cruise Missile Control Aircraft (CXMCA) to radar track cruise missiles and achieve 100 % radar coverage during test flights. The CXNCA was forced to perform a series of intercepts on set point ..."
Abstract
 Add to MetaCart
points recomputed every ton seconds. Fuszy logic formed a vital function in determining wbore the set point would be, and used current and future missile posit4 on data. j This thosis development and completion was only possible through the tireless help and motivation provi4e by my advisor, Col Don
Graph evolution: Densification and shrinking diameters
 ACM TKDD
, 2007
"... How do real graphs evolve over time? What are “normal” growth patterns in social, technological, and information networks? Many studies have discovered patterns in static graphs, identifying properties in a single snapshot of a large network, or in a very small number of snapshots; these include hea ..."
Abstract

Cited by 267 (16 self)
 Add to MetaCart
increase slowly as a function of the number of nodes (like O(log n) or O(log(log n)). Existing graph generation models do not exhibit these types of behavior, even at a qualitative level. We provide a new graph generator, based on a “forest fire” spreading process, that has a simple, intuitive
The Security of the Cipher Block Chaining Message Authentication Code
, 2000
"... Let F be some block cipher (eg., DES) with block length l. The Cipher Block Chaining Message Authentication Code (CBC MAC) specifies that an mblock message x: Xl...xm be authenticated among parties who share a secret key a for the block cipher by tagging x with a prefix of ym, where Y0: 01 and Y ..."
Abstract

Cited by 240 (41 self)
 Add to MetaCart
and Yi: Fa(miYi1) for i: 1,2,...,m. This method is a pervasively used international and U.S. standard. We provide its first formal justification, showing the following general lemma: cipher block chaining a pseudorandom function yields a pseudorandom function. Underlying our results is a technical
1 The Justification of Financial Futures Exchanges
"... The invention of exchangetraded financial futures by commodity exchanges has been justified by Chicagoan financial economics and law and economics on the basis of the unrealistic assumption that trading is costless. Acceptance of this quite circular argument has led to the delegation of extensive p ..."
Abstract
 Add to MetaCart
‘freedom’, there should be stronger public consideration of the optimal publicprivate mix of regulatory governance structures. This paper proposes criteria for the evaluation of the functional justification of exchangetraded futures as a guide for public policy aimed at reducing the volatility
1.5 Summary and justification
"... Christopher Boorse’s Bio Statistical Theory (BST) defines health as the absence of disease, and disease as the adverse departure from normal species functioning. This paper presents a twopronged problem for this account. First I demonstrate that, in order to accurately account for dynamic physiolog ..."
Abstract
 Add to MetaCart
Christopher Boorse’s Bio Statistical Theory (BST) defines health as the absence of disease, and disease as the adverse departure from normal species functioning. This paper presents a twopronged problem for this account. First I demonstrate that, in order to accurately account for dynamic
SemiSupervised Learning on Riemannian Manifolds
, 2004
"... We consider the general problem of utilizing both labeled and unlabeled data to improve classification accuracy. Under the assumption that the data lie on a submanifold in a high dimensional space, we develop an algorithmic framework to classify a partially labeled data set in a principled manner. ..."
Abstract

Cited by 193 (7 self)
 Add to MetaCart
. The central idea of our approach is that classification functions are naturally defined only on the submanifold in question rather than the total ambient space. Using the LaplaceBeltrami operator one produces a basis (the Laplacian Eigenmaps) for a Hilbert space of square integrable functions
ON JUSTIFICATION OF GIBBS DISTRIBUTION 1
, 2001
"... The paper develop a new approach to the justification of Gibbs canonical distribution for Hamiltonian systems with finite number of degrees of freedom. It uses the condition of nonintegrability of the ensemble of weak interacting Hamiltonian systems. 1. Gibbs distribution. We consider the probabilit ..."
Abstract
 Add to MetaCart
The paper develop a new approach to the justification of Gibbs canonical distribution for Hamiltonian systems with finite number of degrees of freedom. It uses the condition of nonintegrability of the ensemble of weak interacting Hamiltonian systems. 1. Gibbs distribution. We consider
Results 1  10
of
1,185