Artificial Neurol Networks in Policy Research: A Current Assessment
Journal of CommunicationPublished 1 March 1993
Joseph Woelfel
Citations71
SJR quartileQ1
SJR score2.53
SNIP2.84
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
Artificial neural networks, modeled, in principle, on idealizations of organic neural structures, exhibit important properties that promise great usefulness for policy researchers and have already found extensive use in areas once reserved for multivariate statistical programs such as regression and multiple classification analysis.
Abstract
Journal Article Artificial Neurol Networks in Policy Research: A Current Assessment Get access Joseph Woelfel Joseph Woelfel 1Joseph Woelfel is professor and chair at the Department of Communication, and senior fellow at the Rockfeller Institute of Government at the State University of New York at Buffalo. Search for other works by this author on: Oxford Academic Google Scholar Journal of Communication, Volume 43, Issue 1, March 1993, Pages 63–80, https://doi.org/10.1111/j.1460-2466.1993.tb01249.x Published: 07 February 2006
Keywords
Computer SciencePhysics and Astronomy
Mathematics of Control Signals and SystemsApproximation by superpositions of a sigmoidal function
13,684 Citations1989George Cybenko
Biological CyberneticsSelf-organized formation of topologically correct feature maps
9,519 Citations1982Teuvo Kohonen
In a simple network of adaptive physical elements which receives signals from a primary event space, the signal representations are automatically mapped onto a set of output responses in such a way that the responses acquire the same topological order as that of the primary events.
Neural NetworksOn the approximate realization of continuous mappings by neural networks
4,220 Citations1989Ken-ichi Funahashi
It is proved that any continuous mapping can be approximately realized by Rumelhart-Hinton-Williams' multilayer neural networks with at least one hidden layer whose output functions are sigmoid functions.
Springer series in information sciencesSelf-Organization and Associative Memory
3,820 Citations1988Teuvo Kohonen
Elsevier eBooksLearning Internal Representations by Error Propagation
3,013 Citations1988David E. Rumelhart, Geoffrey E. Hinton +1 more
This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Neural NetworksIncreased rates of convergence through learning rate adaptation
1,795 Citations1988Robert A. Jacobs
A study of Steepest Descent and an analysis of why it can be slow to converge and four heuristics for achieving faster rates of convergence are proposed.
Applied OpticsART 2: self-organization of stable category recognition codes for analog input patterns
1,433 Citations1987Gail A. Carpenter, Stephen Grossberg
ART 2, a class of adaptive resonance architectures which rapidly self-organize pattern recognition categories in response to arbitrary sequences of either analog or binary input patterns, is introduced.
Cognitive ScienceFeature Discovery by Competitive Learning*
1,073 Citations1985David E. Rumelhart, David Zipser
This paper shows how a set of feature detectors which capture important aspects of the set of stimulus input patterns are discovered and how these feature detectors form the basis of a multilayer system that serves to learn categorizations of stimulus sets which are not linearly separable.
Neural NetworksKolmogorov's theorem and multilayer neural networks
753 Citations1992Věra Kůrková
From a direct proof of the universal approximation capabilities of perceptron type networks with two hidden layers, estimates of numbers of hidden units are derived based on properties of the function being approximation and the accuracy of its approximation.
Neural NetworksImproving the convergence of the back-propagation algorithm
417 Citations1992Arjen van Ooyen, Bernard Nienhuis
The modified back-propagation method consists of a simple change in the total error-of-performance function that is to be minimized by the algorithm, and the final approach to the desired response function is accelerated by an amount that can be predicted analytically.
Neural NetworksSuperSAB: Fast adaptive back propagation with good scaling properties
363 Citations1990Tom Tollenaere
It is shown that SuperSAB may converge orders of magnitude faster than the original back propagation algorithm, and is only slightly instable, while the algorithm is very insensitive to the choice of parameter values, and has excellent scaling properties.
Social NetworksThe NEGOPY network analysis program
125 Citations1981William D. Richards, Ronald E. Rice
The program described here, NEGOPY, is relational, or linkage-based, and the conceptual orientation, computational algorithm, operating characteristics, format and availability of N EGOPY are described.
Neural NetworksRescaling of variables in back propagation learning
103 Citations1991A. K. Rigler, John M. Irvine +1 more
A compensatory rescaling is suggested, based heuristically upon the expected value of the multiplier, which demonstrates an order of magnitude improvement in convergence.
Unsupervised learning in noise
46 Citations1989Kosko
Journal of CommunicationA Mathematical Model for Intercultural Interactions: Making Connections and Increasing Harmony
7 Citations1993G. Blake Armstrong, Isabelle Bauman
The probabilogical inference process underlying negotiation of salient identities is modeled in terms of a type of PDP model of cognitive processing, which demonstrates the impact of marked and unmarked code choices on a hypothetical, simple cognitive system.