Neural networks and simulation: Modeling for applications
SIMULATIONPublished 1 May 1992
Mary Lou Padgett, T. Roppel
Citations31
SJR quartileQ2
SJR score0.38
SNIP0.89
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 simulate biologi cal processes in an intriguing manner and provide an adaptable, robust modeling tool useful to simulationists in all disciplines.
Abstract
Artificial neural networks simulate biologi cal processes in an intriguing manner. Ideas gleaned from the study of neurophysiology and animal behavior have become realizable in recent years. The advent of computers capable of rapidly executing massively parallel and distributed processes has allowed ideas from diverse fields to be merged and tested. The resulting neural networks, simulated in software and/or hardware, provide an adaptable, robust modeling tool useful to simulationists in all disciplines.
Keywords
Computer Science
Proceedings of the IEEENeuromorphic electronic systems
2,202 Citations1990Carver Mead
It is shown that for many problems, particularly those in which the input data are ill-conditioned and the computation can be specified in a relative manner, biological solutions are many orders of magnitude more effective than those using digital methods.
Journal of the Royal Statistical Society Series C (Applied Statistics)Practical Nonparametric Statistics. 2nd Edition.
302 Citations1983R. Allan Reese, W. J. Conover
IEEE Transactions on Neural NetworksBack-propagation learning and nonidealities in analog neural network hardware
90 Citations1991R.C. Frye, Edward A. Rietman +1 more
It is shown that network using large arrays of nonuniform components can perform analog communications with a much higher degree of accuracy than might be expected given the degree of variation in the network's elements.
Neural ComputationThe Effects of Precision Constraints in a Backpropagation Learning Network
77 Citations1990P.W. Hollis, John S. Harper +1 more
It is shown through simulations that a learning system of this nature can be implemented in spite of limited resolution in the analog circuits and using fixed point arithmetic to implement the backpropagation algorithm.
IEEE Transactions on Neural NetworksWeight decay and resolution effects in feedforward artificial neural networks
19 Citations1991D.B. Mundie, L. W. Massengill
If weight decay is unavoidable, bipolar decay achieves an order-of-magnitude better performance than unipolar and that the weight resolution required in actual implementations of feedforward, connectionist hardware is higher than predicted by computer simulations of network responses to random or Gaussian weight perturbations.
IEEE Transactions on Neural NetworksPerformance and generalization of the classification figure of merit criterion function
12 Citations1991Etienne Barnard
It is shown that CFM has optimal training-set performance, which is related to its monotonicity, and there is no reason to expect generalization with this criterion function to be substantially better than that of the standard criterion functions.
IEEE Transactions on Neural NetworksRobust stability analysis of adaptation algorithms for single perceptron
9 Citations1991S. Hui, Stanisław H. Żak
The problem of robust stability and convergence of learning parameters of adaptation algorithms in a noisy environment for the single preceptron is addressed and it is shown that this algorithm is robust and that the weight vectors converge in the presence of bounded noise.
IEEE Transactions on Neural NetworksDetection of spurious states of neural networks
4 Citations1991Yves Crama, Pierre Hansen +1 more
The authors study the complexity and propose an algorithm for the problem of determining, given p vectors of {-1,1}(n), all linear combinations of them which are also in {- 1,1}, which corresponds to the detection of spurious states in neural networks.
IEEE Transactions on Aerospace and Electronic SystemsComments, with reply, on "Optimal detection and performance of distributed sensor systems
4 Citations1989Luciano Izzo, L. Paura +2 more
The detection performance of the distributed system with fusion is developed and the globally optimal system performance is compared with two suboptimal systems.
IEEE Transactions on Semiconductor ManufacturingUsing a test site for the rapid introduction of 32-kb bipolar RAM
3 Citations1992S. Magdo, Meeta S. Gupta
The test-site-aided product introduction doubled the defect learning rate and both the cell layout and processing were optimized with an exploratory test site in the early manufacturing cycle.