Results 1  10
of
46,590
Active Learning with Statistical Models
, 1995
"... For manytypes of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992# Cohn, 1994]. We then showhow the same principles may be used to select data for two alternative, statist ..."
Abstract

Cited by 677 (12 self)
 Add to MetaCart
For manytypes of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992# Cohn, 1994]. We then showhow the same principles may be used to select data for two alternative, statisticallybased learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.
Powerlaw distributions in empirical data
 ISSN 00361445. doi: 10.1137/ 070710111. URL http://dx.doi.org/10.1137/070710111
, 2009
"... Powerlaw distributions occur in many situations of scientific interest and have significant consequences for our understanding of natural and manmade phenomena. Unfortunately, the empirical detection and characterization of power laws is made difficult by the large fluctuations that occur in the t ..."
Abstract

Cited by 589 (7 self)
 Add to MetaCart
Powerlaw distributions occur in many situations of scientific interest and have significant consequences for our understanding of natural and manmade phenomena. Unfortunately, the empirical detection and characterization of power laws is made difficult by the large fluctuations that occur in the tail of the distribution. In particular, standard methods such as leastsquares fitting are known to produce systematically biased estimates of parameters for powerlaw distributions and should not be used in most circumstances. Here we describe statistical techniques for making accurate parameter estimates for powerlaw data, based on maximum likelihood methods and the KolmogorovSmirnov statistic. We also show how to tell whether the data follow a powerlaw distribution at all, defining quantitative measures that indicate when the power law is a reasonable fit to the data and when it is not. We demonstrate these methods by applying them to twentyfour realworld data sets from a range of different disciplines. Each of the data sets has been conjectured previously to follow a powerlaw distribution. In some cases we find these conjectures to be consistent with the data while in others the power law is ruled out.
Term Rewriting Systems
, 1992
"... Term Rewriting Systems play an important role in various areas, such as abstract data type specifications, implementations of functional programming languages and automated deduction. In this chapter we introduce several of the basic comcepts and facts for TRS's. Specifically, we discuss Abstra ..."
Abstract

Cited by 613 (18 self)
 Add to MetaCart
Term Rewriting Systems play an important role in various areas, such as abstract data type specifications, implementations of functional programming languages and automated deduction. In this chapter we introduce several of the basic comcepts and facts for TRS's. Specifically, we discuss Abstract Reduction Systems
SNOPT: An SQP Algorithm For LargeScale Constrained Optimization
, 2002
"... Sequential quadratic programming (SQP) methods have proved highly effective for solving constrained optimization problems with smooth nonlinear functions in the objective and constraints. Here we consider problems with general inequality constraints (linear and nonlinear). We assume that first deriv ..."
Abstract

Cited by 582 (23 self)
 Add to MetaCart
Sequential quadratic programming (SQP) methods have proved highly effective for solving constrained optimization problems with smooth nonlinear functions in the objective and constraints. Here we consider problems with general inequality constraints (linear and nonlinear). We assume that first derivatives are available, and that the constraint gradients are sparse. We discuss
Comprehending Monads
 Mathematical Structures in Computer Science
, 1992
"... Category theorists invented monads in the 1960's to concisely express certain aspects of universal algebra. Functional programmers invented list comprehensions in the 1970's to concisely express certain programs involving lists. This paper shows how list comprehensions may be generalised t ..."
Abstract

Cited by 522 (16 self)
 Add to MetaCart
Category theorists invented monads in the 1960's to concisely express certain aspects of universal algebra. Functional programmers invented list comprehensions in the 1970's to concisely express certain programs involving lists. This paper shows how list comprehensions may be generalised to an arbitrary monad, and how the resulting programming feature can concisely express in a pure functional language some programs that manipulate state, handle exceptions, parse text, or invoke continuations. A new solution to the old problem of destructive array update is also presented. No knowledge of category theory is assumed.
Parametric Shape Analysis via 3Valued Logic
, 2001
"... Shape Analysis concerns the problem of determining "shape invariants"... ..."
Abstract

Cited by 660 (79 self)
 Add to MetaCart
Shape Analysis concerns the problem of determining "shape invariants"...
Simultaneous Multithreading: Maximizing OnChip Parallelism
, 1995
"... This paper examines simultaneous multithreading, a technique permitting several independent threads to issue instructions to a superscalar’s multiple functional units in a single cycle. We present several models of simultaneous multithreading and compare them with alternative organizations: a wide s ..."
Abstract

Cited by 802 (48 self)
 Add to MetaCart
This paper examines simultaneous multithreading, a technique permitting several independent threads to issue instructions to a superscalar’s multiple functional units in a single cycle. We present several models of simultaneous multithreading and compare them with alternative organizations: a wide superscalar, a finegrain multithreaded processor, and singlechip, multipleissue multiprocessing architectures. Our results show that both (singlethreaded) superscalar and finegrain multithreaded architectures are limited in their ability to utilize the resources of a wideissue processor. Simultaneous multithreading has the potential to achieve 4 times the throughput of a superscalar, and double that of finegrain multithreading. We evaluate several cache configurations made possible by this type of organization and evaluate tradeoffs between them. We also show that simultaneous multithreading is an attractive alternative to singlechip multiprocessors; simultaneous multithreaded processors with a variety of organizations outperform corresponding conventional multiprocessors with similar execution resources. While simultaneous multithreading has excellent potential to increase processor utilization, it can add substantial complexity to the design. We examine many of these complexities and evaluate alternative organizations in the design space.
Parallel Networks that Learn to Pronounce English Text
 COMPLEX SYSTEMS
, 1987
"... This paper describes NETtalk, a class of massivelyparallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed h ..."
Abstract

Cited by 548 (5 self)
 Add to MetaCart
This paper describes NETtalk, a class of massivelyparallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed human performance. (i) The learning follows a power law. (;i) The more words the network learns, the better it is at generalizing and correctly pronouncing new words, (iii) The performance of the network degrades very slowly as connections in the network are damaged: no single link or processing unit is essential. (iv) Relearning after damage is much faster than learning during the original training. (v) Distributed or spaced practice is more effective for longterm retention than massed practice. Network models can be constructed that have the same performance and learning characteristics on a particular task, but differ completely at the levels of synaptic strengths and singleunit responses. However, hierarchical clustering techniques applied to NETtalk reveal that these different networks have similar internal representations of lettertosound correspondences within groups of processing units. This suggests that invariant internal representations may be found in assemblies of neurons intermediate in size between highly localized and completely distributed representations.
Computer support for knowledgebuilding communities
 The Journal of the Learning Sciences
, 1994
"... Nobody wants to use technology to recreate education as it is, yet there is not much to distinguish what goes on in most computersupported classrooms versus traditional classrooms. Kay (1991) has suggested that the phenomenon of reframing innovations to recreate the familiar is itself commonplace. ..."
Abstract

Cited by 593 (4 self)
 Add to MetaCart
Nobody wants to use technology to recreate education as it is, yet there is not much to distinguish what goes on in most computersupported classrooms versus traditional classrooms. Kay (1991) has suggested that the phenomenon of reframing innovations to recreate the familiar is itself commonplace. Thus, one sees all manner of powerful technology (Hypercard, CDROM, Lego Logo, and so forth) used to conduct shopworn school activities: copying material from one resource into another (e.g., using Hypercard to assemble sound and visual bites produced by others), and following stepbystep procedures (e.g., creating Lego Logo machines by following steps in a manual). With new technologies, studentgenerated collages and reproductions appear more inventive and sophisticatedwith impressive displays of sound, video, and typographybut from a cognitive perspective, it is not clear what, if any, knowledge content has been processed by the students. In this chapter we offer a suggestion for how to escape the pattern of reinventing the familiar with educational technology. Knowledgebuilding discourse is at the heart of the superior education that we have in mind. We argue that the classroom needs to foster
Finding community structure in networks using the eigenvectors of matrices
, 2006
"... We consider the problem of detecting communities or modules in networks, groups of vertices with a higherthanaverage density of edges connecting them. Previous work indicates that a robust approach to this problem is the maximization of the benefit function known as “modularity ” over possible div ..."
Abstract

Cited by 500 (0 self)
 Add to MetaCart
We consider the problem of detecting communities or modules in networks, groups of vertices with a higherthanaverage density of edges connecting them. Previous work indicates that a robust approach to this problem is the maximization of the benefit function known as “modularity ” over possible divisions of a network. Here we show that this maximization process can be written in terms of the eigenspectrum of a matrix we call the modularity matrix, which plays a role in community detection similar to that played by the graph Laplacian in graph partitioning calculations. This result leads us to a number of possible algorithms for detecting community structure, as well as several other results, including a spectral measure of bipartite structure in networks and a new centrality measure that identifies those vertices that occupy central positions within the communities to which they belong. The algorithms and measures proposed are illustrated with applications to a variety of realworld complex networks.
Results 1  10
of
46,590