Results 1  10
of
817,589
Restoration of a Single Superresolution Image from Several Blurred, Noisy, and Undersampled Measured Images
, 1997
"... The three main tools in the single image restoration theory are the maximum likelihood (ML) estimator, the maximum a posteriori probability (MAP) estimator, and the set theoretic approach using projection onto convex sets (POCS). This paper utilizes the above known tools to propose a unified methodo ..."
Abstract

Cited by 267 (22 self)
 Add to MetaCart
The three main tools in the single image restoration theory are the maximum likelihood (ML) estimator, the maximum a posteriori probability (MAP) estimator, and the set theoretic approach using projection onto convex sets (POCS). This paper utilizes the above known tools to propose a unified
Addressing the Curse of Imbalanced Training Sets: OneSided Selection
 In Proceedings of the Fourteenth International Conference on Machine Learning
, 1997
"... Adding examples of the majority class to the training set can have a detrimental effect on the learner's behavior: noisy or otherwise unreliable examples from the majority class can overwhelm the minority class. The paper discusses criteria to evaluate the utility of classifiers induced f ..."
Abstract

Cited by 234 (1 self)
 Add to MetaCart
from such imbalanced training sets, gives explanation of the poor behavior of some learners under these circumstances, and suggests as a solution a simple technique called onesided selection of examples. 1 Introduction The general topic of this paper is learning from examples described by pairs
(Ml
, 1986
"... The SLAC Linear Collider (SLC) is a variation of a new class of colliders whereby two linear accelerators are aimed at each other to collide intense bunches of electrons and positrons together. Conventional storage rings are becoming ever more costly as the energy of the stored beams increases such ..."
Abstract
 Add to MetaCart
The SLAC Linear Collider (SLC) is a variation of a new class of colliders whereby two linear accelerators are aimed at each other to collide intense bunches of electrons and positrons together. Conventional storage rings are becoming ever more costly as the energy of the stored beams increases such that the cost of two linear colliders per GeV is less than that of electronpositron storage rings at c.m. energies above about 100 GeV. The SLC being built at SLAC is designed to achieve a centerofmass energy of 100 GeV by accelerating intense bunches of particles, both electrons and positrons, in the SLAC linac and transporting them along two different arcs to a point where they’re focused to a small radius and made to collide head on. The SLC has two main goals. The first is to develop the physics and technology of linear colliders. The other is to achieve centerofmass energies above 90 GeV in order to investigate the unification of the weak and electromagnetic interactions in the energy range above 90 GeV; (i.e., ZO, etc.). This note discusses a few of the special problems that were encountered by the Radiation Physics group at SLAC during the design and construction of the SLAC Linear Collider. The nature of these problems is discussed along with the methods employed to solve them.
A Critique of Standard ML
, 1992
"... Standard ML is an excellent language for many kinds of programming. It is safe, efficient, suitably abstract, and concise. There are many aspects of the language that work well. However, nothing is perfect: Standard ML has a few shortcomings. In some cases there are obvious solutions, and in other c ..."
Abstract

Cited by 100 (4 self)
 Add to MetaCart
Standard ML is an excellent language for many kinds of programming. It is safe, efficient, suitably abstract, and concise. There are many aspects of the language that work well. However, nothing is perfect: Standard ML has a few shortcomings. In some cases there are obvious solutions, and in other
On Contrastive Divergence Learning
"... Maximumlikelihood (ML) learning of Markov random fields is challenging because it requires estimates of averages that have an exponential number of terms. Markov chain Monte Carlo methods typically take a long time to converge on unbiased estimates, but Hinton (2002) showed that if the Markov ..."
Abstract

Cited by 129 (14 self)
 Add to MetaCart
and show that it provides biased estimates in general, but that the bias is typically very small. Fast CD learning can therefore be used to get close to an ML solution and slow ML learning can then be used to finetune the CD solution.
Type Inference for Records in a Natural Extension of ML
 Theoretical Aspects of ObjectOriented Programming: Types, Semantics, and Language Design
, 1994
"... We describe an extension of ML with records where inheritance is given by ML generic polymorphism. All common operations on records but concatenation are supported, in particular the free extension of records. Other operations such as renaming of fields are added. The solution relies on an extension ..."
Abstract

Cited by 88 (10 self)
 Add to MetaCart
We describe an extension of ML with records where inheritance is given by ML generic polymorphism. All common operations on records but concatenation are supported, in particular the free extension of records. Other operations such as renaming of fields are added. The solution relies
Abyssal recipes
 DeepSea Res
, 1966
"... AbstractVertical distributions in the interior Pacific (excluding tbe top and bottom kilometer) are not inzonsistent with a simple model involving aconstant upward vertical velozity w ~ 12 cm clu yt and eddy diffusivity, ¢ ~ 1.3 cm ~ sec1. Thus temperature and salinity can be fitted by expone ..."
Abstract

Cited by 173 (0 self)
 Add to MetaCart
by exponentiallike solutions to [,¢ d"/dz: w. d/d:] T, S = 0, with,c/w ~ 1 km the appropriate " ' scale height." For Carbon 14 a decay term must be included, [ ]:~C = ~ 1~C; a fitting of the solution to the observed 1~C distribution yields,,/w2 ~ 200 years for the appropriate "
Compact Algorithm for Strictly ML Ellipse Fitting
"... A very compact algorithm is presented for fitting an ellipse to points in images by maximum likelihood (ML) in the strict sense. Although our algorithm produces the same solution as existing MLbased methods, it is probably the simplest and the smallest of all. By numerical experiments, we show that ..."
Abstract

Cited by 6 (5 self)
 Add to MetaCart
A very compact algorithm is presented for fitting an ellipse to points in images by maximum likelihood (ML) in the strict sense. Although our algorithm produces the same solution as existing MLbased methods, it is probably the simplest and the smallest of all. By numerical experiments, we show
Functorial ML
, 1996
"... . We present an extension of the HindleyMilner type system that supports a generous class of type constructors called functors, and provide a parametrically polymorphic algorithm for their mapping, i.e. for applying a function to each datum appearing in a value of constructed type. The algorithm co ..."
Abstract

Cited by 27 (9 self)
 Add to MetaCart
. We present an extension of the HindleyMilner type system that supports a generous class of type constructors called functors, and provide a parametrically polymorphic algorithm for their mapping, i.e. for applying a function to each datum appearing in a value of constructed type. The algorithm comes from shape theory, which provides a uniform method for locating data within a shape. The resulting system is ChurchRosser and strongly normalising, and supports type inference. 1 Introduction The interplay between type theory, programming language semantics and category theory is now well established. Two of the strongest examples of this interaction are the representation of function types as exponential objects in a cartesian closed category [LS86] and the description of polymorphic terms as natural transformations (e.g. [BFSS90]). For example, the operation of appending lists can be represented as a natural transformation LL)L where L: D ! D is the list functor on some category D. ...
Nonrigid point set registration: Coherent Point Drift (CPD)
 IN ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 19
, 2006
"... We introduce Coherent Point Drift (CPD), a novel probabilistic method for nonrigid registration of point sets. The registration is treated as a Maximum Likelihood (ML) estimation problem with motion coherence constraint over the velocity field such that one point set moves coherently to align with ..."
Abstract

Cited by 141 (0 self)
 Add to MetaCart
with the second set. We formulate the motion coherence constraint and derive a solution of regularized ML estimation through the variational approach, which leads to an elegant kernel form. We also derive the EM algorithm for the penalized ML optimization with deterministic annealing. The CPD method
Results 1  10
of
817,589