Results 1  10
of
3,509
Variational algorithms for approximate Bayesian inference
, 2003
"... The Bayesian framework for machine learning allows for the incorporation of prior knowledge in a coherent way, avoids overfitting problems, and provides a principled basis for selecting between alternative models. Unfortunately the computations required are usually intractable. This thesis presents ..."
Abstract

Cited by 440 (9 self)
 Add to MetaCart
The Bayesian framework for machine learning allows for the incorporation of prior knowledge in a coherent way, avoids overfitting problems, and provides a principled basis for selecting between alternative models. Unfortunately the computations required are usually intractable. This thesis presents
: The exponential,
"... , progress of electronics may be continued beyond the 10nm frontier if the currently dominant CMOS technology is replaced by hybrid CMOL circuits combining a silicon MOSFET stack and a few layers of parallel nanowires connected by selfassembled molecular electronic devices. Such hybrids promise ..."
Abstract
 Add to MetaCart
unparalleled performance for advanced information processing, but require special architectures to compensate for specific features of the molecular devices, including low voltage gain and possible high fraction of faulty components. Neuromorphic networks with their defect tolerance seem the most natural way
Statistical Models for Text Segmentation
 Machine Learning
, 1999
"... . This paper introduces a new statistical approach to automatically partitioning text into coherent segments. The approach is based on a technique that incrementally builds an exponential model to extract features that are correlated with the presence of boundaries in labeled training text. The mode ..."
Abstract

Cited by 273 (2 self)
 Add to MetaCart
. This paper introduces a new statistical approach to automatically partitioning text into coherent segments. The approach is based on a technique that incrementally builds an exponential model to extract features that are correlated with the presence of boundaries in labeled training text
PEGASUS: A policy search method for large MDPs and POMDPs
 In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence
, 2000
"... We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model. Our approach is based on the following observation: Any (PO)MDP can be transformed into an "equivalent&qu ..."
Abstract

Cited by 257 (9 self)
 Add to MetaCart
;equivalent" POMDP in which all state transitions (given the current state and action) are deterministic. This reduces the general problem of policy search to one in which we need only consider POMDPs with deterministic transitions. We give a natural way of estimating the value of all policies
The Helmholtz Machine
, 1995
"... Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative model ..."
Abstract

Cited by 238 (24 self)
 Add to MetaCart
models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns. We describe a way of finessing this combinatorial explosion by maximizing an easily computed lower bound on the probability
Reasoning about The Past with TwoWay Automata
 In 25th International Colloqium on Automata, Languages and Programming, ICALP ’98
, 1998
"... Abstract. The pcalculus can be viewed as essentially the "ultimate" program logic, as it expressively subsumes all propositional program logics, including dynamic logics, process logics, and temporal logics. It is known that the satisfiability problem for the pcalculus is EXPTIMEcomplete ..."
Abstract

Cited by 160 (14 self)
 Add to MetaCart
calculus is EXPTIMEcomplete. This upper bound, however, is known for a version of the logic that has only forward modalities, which express weakest preconditions, but not backward modalities, which express strongest postconditions. Our main result in this paper is an exponential time upper bound for the satisfiability
Performance and Stability of Communication Networks via Robust Exponential Bounds
 IEEE/ACM Transactions on Networking
, 1993
"... We propose a new way for evaluating the performance of packet switching communication networks under a fixed (session based) routing strategy. Our approach is based on properly bounding the probability distribution functions of the system input processes. The bounds we suggest, which are decaying ex ..."
Abstract

Cited by 150 (3 self)
 Add to MetaCart
We propose a new way for evaluating the performance of packet switching communication networks under a fixed (session based) routing strategy. Our approach is based on properly bounding the probability distribution functions of the system input processes. The bounds we suggest, which are decaying
A powerdomain construction
 SIAM J. OF COMPUTING
, 1976
"... We develop a powerdomain construction, [.], which is analogous to the powerset construction and also fits in with the usual sum, product and exponentiation constructions on domains. The desire for such a construction arises when considering programming languages with nondeterministic features or p ..."
Abstract

Cited by 234 (15 self)
 Add to MetaCart
We develop a powerdomain construction, [.], which is analogous to the powerset construction and also fits in with the usual sum, product and exponentiation constructions on domains. The desire for such a construction arises when considering programming languages with nondeterministic features
Analysis of some Krylov subspace approximations to the matrix exponential operator
 SIAM J. Numer. Anal
, 1992
"... Abstract. In this note we present a theoretical analysis of some Krylov subspace approximations to the matrix exponential operation exp(A)v and establish a priori and a posteriori error estimates. Several such approximations are considered. The main idea of these techniques is to approximately proje ..."
Abstract

Cited by 135 (7 self)
 Add to MetaCart
project the exponential operator onto a small Krylov subspace and carry out the resulting small exponential matrix computation accurately. This general approach, which has been used with success in several applications, provides a systematic way of defining high order explicittype schemes for solving
Results 1  10
of
3,509