Neural Networks and Related 'Massively Parallel' Methods for Statistics: A Short Overview
International Statistical ReviewPublished 1 December 1994
F. Murtagh
Citations20
SJR quartileQ1
SJR score0.92
SNIP1.84
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Neural networks and other related problem-solving methods have been applied to various statistical problems and their relevance to centers and institutes concerned with the processing of large collections of data is reviewed.
Abstract
Summary Neural networks and other related problem-solving methods have been applied to various statistical problems. We review some of these methods, and application areas, together with their relevance to centers and institutes concerned with the processing of large collections of data.
Keywords
Computer ScienceEngineering
Neural NetworksMultilayer feedforward networks are universal approximators
21,248 Citations1989Kurt Hornik, Maxwell B. Stinchcombe +1 more
It is rigorously established that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available.
Proceedings of the National Academy of SciencesNeural networks and physical systems with emergent collective computational abilities.
19,349 Citations1982J. J. Hopfield
A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Genetic Algorithms in Search, Optimization and Machine Learning
17,773 Citations1988David E. Goldberg, David Robson
Springer series in information sciencesSelf-Organization and Associative Memory
8,770 Citations1989Teuvo Kohonen
IEEE ASSP MagazineAn introduction to computing with neural nets
7,858 Citations1987Richard P. Lippmann
Proceedings of the National Academy of SciencesNeurons with graded response have collective computational properties like those of two-state neurons.
6,955 Citations1984J. J. Hopfield
A model for a large network of "neurons" with a graded response (or sigmoid input-output relation) is studied and collective properties in very close correspondence with the earlier stochastic model based on McCulloch - Pitts neurons are studied.
Biological Cybernetics“Neural” computation of decisions in optimization problems
6,040 Citations1985J. J. Hopfield, David W. Tank
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks.
Proceedings of the IEEEBackpropagation through time: what it does and how to do it
4,904 Citations1990Paul J. Werbos
This paper first reviews basic backpropagation, a simple method which is now being widely used in areas like pattern recognition and fault diagnosis, and describes further extensions of this method, to deal with systems other than neural networks, systems involving simultaneous equations or true recurrent networks, and other practical issues which arise with this method.
Machine LearningLearning to Predict by the Methods of Temporal Differences
3,894 Citations1988Richard S. Sutton
This article introduces a class of incremental learning procedures specialized for prediction-that is, for using past experience with an incompletely known system to predict its future behavior, and proves their convergence and optimality for special cases and relate them to supervised-learning methods.
Neural ComputationNeural Networks and the Bias/Variance Dilemma
3,563 Citations1992Stuart Geman, Elie Bienenstock +1 more
It is suggested that current-generation feedforward neural networks are largely inadequate for difficult problems in machine perception and machine learning, regardless of parallel-versus-serial hardware or other implementation issues.
IEEE Transactions on ComputersA Nonlinear Mapping for Data Structure Analysis
3,381 Citations1969John W. Sammon
An algorithm for the analysis of multivariate data is presented along with some experimental results that is based upon a point mapping of N L-dimensional vectors from the L-space to a lower-dimensional space such that the inherent data "structure" is approximately preserved.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)The Cascade-Correlation learning architecture
2,401 Citations2018Scott E. Fahlman, Christian Lebière
The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.
Neural NetworksAnalysis of hidden units in a layered network trained to classify sonar targets
1,111 Citations1988Rebecca Gorman, Terrence J. Sejnowski
A neural network learning procedure has been applied to the classification of sonar returns from two undersea targets, a metal cylinder and a similarly shaped rock, and network performance and classification strategy was comparable to that of trained human listeners.
Neural NetworksGeneralization of backpropagation with application to a recurrent gas market model
952 Citations1988Paul J. Werbos
This paper will derive a generalization of backpropagation to recurrent systems (which input their own output), such as hybrids of perceptron-style networks and Grossberg/Hopfield networks, and does not require the storage of intermediate iterations to deal with continuous recurrence.
Proceedings of the IEEEVector quantization in speech coding
845 Citations1985J. Makhoul, S. Roucos +1 more
This tutorial review presents the basic concepts employed in vector quantization and gives a realistic assessment of its benefits and costs when compared to scalar quantization, and focuses primarily on the coding of speech signals and parameters.
NatureAn analogue approach to the travelling salesman problem using an elastic net method
810 Citations1987Richard Durbin, David Willshaw
This work describes how a parallel analogue algorithm, derived from a formal model for the establishment of topographically ordered projections in the brain, can be applied to the travelling salesman problem, and produces shorter tour lengths than another recent parallel analogue algorithms.
Bayesian methods for adaptive models
629 Citations1992David Mackay
The Bayesian framework for model comparison and regularisation is demonstrated by studying interpolation and classification problems modelled with both linear and non-linear models, and it is shown that the careful incorporation of error bar information into a classifier's predictions yields improved performance.
Neural NetworksSelf-organizing feature maps and the travelling salesman problem
341 Citations1988Bernard Angéniol, Gaël de La Croix Vaubois +1 more
Based on Kohonen's work on self-organizing feature maps, an algorithm for solving the classical Travelling Salesman Problem is derived, given a set of cities defined by their positions in the plane, which iteratively organizes towards a quasi-optimal solution.
National Conference on Artificial IntelligenceSolving large-scale constraint satisfaction and scheduling problems using a heuristic repair method
276 Citations1990Steven Minton, Mark Johnston +2 more
A theoretical analysis is presented to explain why the heuristic method for solving large-scale constraint satisfaction and scheduling problems works so well on certain types of problems and to predict when it is likely to be most effective.
Elsevier eBooksBACK-PROPAGATION, WEIGHT-ELIMINATION AND TIME SERIES PREDICTION
177 Citations1991Andreas S. Weigend, David E. Rumelhart +1 more
This work analyzes the sunspot series as an example of a real world time series of limited record length and finds that sigmoid networks trained with weight-elimination outperform traditional nonlinear statistical approaches.
IEEE Transactions on Fuzzy SystemsSelf-organization for object extraction using a multilayer neural network and fuzziness measures
156 Citations1993Ashish Ghosh, Nikhil R. Pal +1 more
A self-organizing multilayer neural network architecture suitable for image processing that does not require any supervised learning is proposed and an application of the proposed network in object extraction from noisy scenes is demonstrated.
Proceedings of the IEEEA performance comparison of trained multilayer perceptrons and trained classification trees
112 Citations1990Les Atlas, Ronald A. Cole +6 more
Selecting neural network architectures via the prediction risk: application to corporate bond rating prediction
104 Citations2002Joachim Utans, John Moody
The authors propose the prediction risk as a measure of the generalization ability of multi-layer perceptron networks and use it to select the optimal network architecture.
ScienceA Near-Optimum Parallel Planarization Algorithm
102 Citations1989Yoshiyasu Takefuji, Kuo-Chun Lee
A near-optimum parallel planarization algorithm, composed of an N x N neural network array, not only generates a near-maximal planar subgraph from a nonplanar graph or a planar graph but also embeds the subgraph on a single plane within 0(1) time.
Artificial neural network for nonlinear projection of multivariate data
66 Citations2003Anil K. Jain, Jianchang Mao
Experimental results indicate that the projection network has good generalization capability when an appropriately sized training set and network are utilized, and a lower bound for the number of free parameters required to achieve the same representation power as Shannon's algorithm is derived.
IEEE Transactions on Systems Man and CyberneticsA comparison between criterion functions for linear classifiers, with an application to neural nets
64 Citations1989Etienne Barnard, David Casasent
The error rates of linear classifiers that utilize various criterion functions are investigated for the case of two normal distributions with different variances and a priori probabilities, finding that the classifier based on the least mean squares criterion often performs considerably worse than the Bayes rate.
Computers & Operations ResearchScheduling with neural networks—the case of the hubble space telescope
49 Citations1992Mark Johnston, H. M. Adorf
Equipped with a novel stochastic neuron update rule, the resulting GDS-network effectively implements a Las Vegas-type algorithm to generate good schedules with an unparalleled efficiency.
Elsevier eBooksSTATISTICAL PATTERN RECOGNITION REVISITED
42 Citations1990Teuvo Kohonen
It has now turned out that certain new self-organizing approaches, here grouped under the title Learning Vector Quantization (LVQ), can combine theoretically near-optimal accuracy with very high speed in learning and recognition and their implementation by analog VLSI is straightforward.
Computer Vision Graphics and Image ProcessingSimultaneous fitting of several planes to point sets using neural networks
26 Citations1990Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi +1 more
This problem is prototypical of a class of problems in computer vision, pattern recognition, and data fitting, and it is shown that given a tolerance one can determine the number of lines that should be fitted to a given point configuration.
Studies in classification, data analysis, and knowledge organizationThe Multilayer Perceptron for Discriminant Analysis: Two Examples
9 Citations1992F. Murtaghl
Assessment of the use of the multilayer perceptron for discriminant analysis tasks finds that results obtained are at least as good as those obtained using this discriminantAnalysis of k-Nearest Neighbours.
Studies in classification, data analysis, and knowledge organizationClassification with neural networks
7 Citations1991Albert Müller, John von Neumann
Classificatory abilities of neural networks, problems of preprocessing of spectral data and their analysis by backpropagation are discussed, and there will be a short comparison between (higher order) associative memories and discriminant analysis.