Neural Networks for the MS/OR Analyst: An Application Bibliography
INFORMS Journal on Applied AnalyticsPublished 1 April 1994
Ramesh Sharda
Citations182
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
This annotated bibliography of application literature should offer a nontechnical fast track to someone getting started in this exciting area of neural networks and management science.
Abstract
From a management scientist's perspective, the neural networks offer three opportunities: statistical methods, optimization methods, and a problem domain in which to apply OR algorithms. This annotated bibliography of application literature should offer a nontechnical fast track to someone getting started in this exciting area. The research published thus far on the applications of neural networks for statistical and optimization problems shows promise for the interface of neural networks and management science.
Keywords
Computer ScienceDecision Sciences
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.
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.
IEEE Transactions on Circuits and SystemsSimple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit
2,173 Citations1986David W. Tank, J. J. Hopfield
It is described how several optimization problems can be rapidly solved by highly interconnected networks of simple analog processors, and it is shown that a network which solves linear programming Problems can be understood from the same concepts.
Neural NetworksUniversal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
2,086 Citations1990Kurt Hornik, Maxwell B. Stinchcombe +1 more
A shoulder strap retainer having a base to be positioned on the exterior shoulder portion of a garment with securing means attached to the undersurface of the base for removably securing the base to the exterior shoulders portion of the garment.
Journal of ForecastingThe accuracy of extrapolation (time series) methods: Results of a forecasting competition
1,469 Citations1982Spyros Makridakis, A. Andersen +7 more
The results of a forecasting competition are presented to provide empirical evidence about differences found to exist among the various extrapolative (time series) methods used in the competition.
Management ScienceManagerial Applications of Neural Networks: The Case of Bank Failure Predictions
1,124 Citations1992Kar Yan Tam, Melody Y. Kiang
Empirical results show that neural nets is a promising method of evaluating bank conditions in terms of predictive accuracy, adaptability, and robustness.
IEEE Transactions on Circuits and SystemsNeural networks for nonlinear programming
1,111 Citations1988Michael Peter Kennedy, Leon O. Chua
By considering the total cocontent function, the solution of the canonical non linear programming circuit is reconciled with the problem being modeled and it is shown how the circuit can be realized using a neural network, thereby extending the results of D.W. Tank and J.J. Hopefield to the general nonlinear programming problem.
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.
Neural ComputationLearning in Artificial Neural Networks: A Statistical Perspective
922 Citations1989Halbert White
Concepts and analytical results from the literatures of mathematical statistics, econometrics, systems identification, and optimization theory relevant to the analysis of learning in artificial neural networks are reviewed.
A neural network model for bankruptcy prediction
847 Citations1990Marcus D. Odom, Ramesh Sharda
A comparison of the predictive abilities of both the neural network and the discriminant analysis method for bankruptcy prediction shows that neural networks might be applicable to this problem.
Optimization methods & softwareRobust linear programming discrimination of two linearly inseparable sets
784 Citations1992Kristin P. Bennett, O. L. Mangasarian
A single linear programming formulation is proposed which generates a plane that of minimizes an average sum of misclassified points belonging to two disjoint points sets in n-dimensional real space, without the imposition of extraneous normalization constraints that inevitably fail to handle certain cases.
Decision Support SystemsBankruptcy prediction using neural networks
721 Citations1994Rick L. Wilson, Ramesh Sharda
The study indicates that neural networks perform significantly better than discriminant analysis at predicting firm bankruptcies, and implications for the accounting professional, neural networks researcher and decision support system builders are highlighted.
ASME Press eBooksIntelligent Engineering Systems through Artificial Neural Networks
611 Citations2009Artificial Neural Networks in Engineering Conference < 2009, Saint Louis, Mo.>, Dagli, Cihan H. +1 more
Decision SciencesNeural Networks: A New Tool for Predicting Thrift Failures*
534 Citations1992Linda Salchenberger, E. Mine Çinar +1 more
A neural network model that processes input data consisting of financial ratios is developed to predict the financial health of thrift institutions and its ability to discriminate between healthy and failed institutions is compared to a traditional statistical model.
International Journal of ForecastingArtificial neural network models for forecasting and decision making
443 Citations1994Tim Hill, Leorey Marquez +2 more
The need to consider the many mathematical proofs underlying artificial neural networks to determine the best conditions for their use in forecasting and decision making is noted.
SIMULATIONTime series forecasting using neural networks vs. Box- Jenkins methodology
406 Citations1991Zaiyong Tang, Chrys de Almeida +1 more
It is found that for time series of different complexities there are optimal neural network topologies and parameters that enable them to learn more efficiently and are also parsimonious in their data requirements.
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.
Stock price pattern recognition-a recurrent neural network approach
254 Citations1990Keita Kamijo, T. Tanigawa
Recurrent neural networks were applied to the recognition of stock patterns, and a method for evaluating the networks was developed that is applicable to reducing mismatching patterns.
Predicting stock price performance: a neural network approach
182 Citations2002Youngohc Yoon, George Swales
The purpose of this paper is to examine the capability of a neural network method and compares its predictive power with that of multiple discriminant analysis methods.
Journal of Intelligent ManufacturingConnectionist approach to time series prediction: an empirical test
181 Citations1992Ramesh Sharda, Rajendra B. Patil
The results show that the simple neural net model tested on this set of time series could forecast about as well as the Box-Jenkins automatic forecasting expert system.
Time series forecasting using neural networks
175 Citations1994Thomas Kolarik, Gottfried Rudorfer
This paper presents an APL system for forecasting univariate time series with artificial neural networks that delivered a better forecasting performance than results obtained by the well known ARIMA technique.
Neural networks for bond rating improved by multiple hidden layers
133 Citations1990Alvin J. Surkan, J. Clay Singleton
These experiments suggest that networks trained with two hidden layers outperform a network having only one hidden layer containing a comparable number of processing elements, when the task was presented as one of separating two noncontiguous classes.
Neural NetworksThe optimised internal representation of multilayer classifier networks performs nonlinear discriminant analysis
121 Citations1990Andrew R. Webb, David Lowe
This paper illustrates why a nonlinear adaptive feed-forward layered network with linear output units can perform well as a pattern classification device and shows that minimising the error at the output of the network is equivalent to maximising a particular norm, the network discriminant function, at theoutput of the hidden units.
IEEE International Conference on Neural NetworksAn application of a multiple neural network learning system to emulation of mortgage underwriting judgements
106 Citations1988Collins, Ghosh +1 more
It was found that when the MNNLS system and the underwriters disagree, the system's classifications are more consistent with the guidelines than the underwriter's judgement.
Function approximation and time series prediction with neural networks
104 Citations1990R.D. Jones, Y.C. Lee +5 more
It is shown that a one-dimensional Newton method is quite fast and reasonably accurate and the use of an adaptable gradient and normalized basis functions can significantly reduce the amount of data necessary to train the net while maintaining the speed advantage of a net that is linear in the weights.
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.
Computers & Operations ResearchNeural network methods in combinatorial optimization
103 Citations1992Chee‐Kit Looi
These approaches suggest neural network methods as an alternative for solving certain optimization tasks as compared to classical optimization techniques and other novel approaches like simulated annealing.
INFORMS Journal on ComputingA Neural Network-Based Optimization Algorithm for the Static Weapon-Target Assignment Problem
91 Citations1989E. Wacholder
A neural network-based algorithm was developed for the static weapon-target assignment problem in ballistic missile defense and has proven to be stable and to converge to solutions very close to global optima.
Computers & Operations ResearchA feedforward neural network for multiple criteria decision making
90 Citations1992Jun Wang, Behnam Malakooti
This paper presents a feedforward neural network for solving discrete multiple criteria decision problems under certainty and specifies two types of multiattribute decision models and analyzes some desirable properties associated with supervised learning.
Computers & Operations ResearchNeural networks and operations research: An overview
85 Citations1992Laura I. Burke, James P. Ignizio
The neural network approach is introduced, from an OR perspective—and just where and how such a tool might find application is indicated.
IEEE International Conference on Neural NetworksDetermination of parameters in a Hopfield/Tank computational network
83 Citations1988Hedge, Sweet +1 more
The authors examine the traveling salesperson problem (TSP) as a representative NP-complete optimization problem and presents a cookbook approach to setting parameters, finding a linear relationship between two of the parameters.
IEEE International Conference on Neural NetworksOptimization by neural networks
80 Citations1988J. Ramanujam, Sadayappa
This proposal shows how to map combinational optimization problems, including graph K-partitioning, vertex cover, maximum independent set, maximum clique, number partitioning, and maximum matching, and reports that performance results are quite encouraging.
Journal of Intelligent ManufacturingNeural network-based design of cellular manufacturing systems
79 Citations1991C�sar O. Malav�, Satheesh Ramachandran
This paper presents an approach where knowledge is extracted from the external and internal structure of the neural network.
Neural network implementation of the shortest path algorithm for traffic routing in communication networks
66 Citations1989L. Zhang, Stelios C. A. Thomopoulos
Neural network models as an alternative to regression
65 Citations2002Leorey Marquez, Tim Hill +2 more
The results of this study indicate that neural network models perform best under conditions of high noise and low sample size, and with less noise or larger sample sizes, they become less competitive.
Computers & Industrial EngineeringA unified group technology implementation using the backpropagation learning rule of neural networks
63 Citations1991Yu‐Lin Kao, Young B. Moon
A feedforward neural network using the Backpropagation learning rule is adopted to automatically generate part families during the part classification process, and a heuristic algorithm using the neural network is described with an illustrative example.
Computers & Operations ResearchThe guilty net for the traveling salesman problem
58 Citations1992Laura I. Burke, Poulomi Damany
A new, adaptive neural structure is proposed for solving the traveling salesman problem, and the guilty net, an even more recent adaptive approach, utilizes a straightforward competitive learning algorithm with fixed neighbors and “conscience” to automatically generate valid, short tours in only a few hundred iterations.
A neural network application for bankruptcy prediction
51 Citations2002W. Raghupathi, Lawrence L. Schkade +1 more
Results of simulations with one and two hidden layers with varying nodes are presented and it appears that neural network algorithms can be investigated further as potential models for bankruptcy prediction.
Journal of Intelligent ManufacturingTool condition monitoring in metal cutting: A neural network approach
50 Citations1991Laura I. Burke, Sabbir Rangwala
The application of supervised and unsupervised neural network paradigms to pattern recognition of sensor signal features supports the premise that, despite excellent classification accuracy by both networks, the unsuper supervised system holds greater promise in a real world setting.
Computers & Operations ResearchPredicting salinity in the chesapeake bay using backpropagation
46 Citations1992Lenore DeSilet, Bruce Golden +2 more
A simple neural network approach with regression models is compared with respect to survey data gathered in the same time period as the one used to construct the models and on new survey data and in general, the neural network models predict salinity value better than the corresponding regression models.
Computers & Operations ResearchRecurrent neural networks for linear programming: Analysis and design principles
42 Citations1992Jun Wang, Vira Chankong
The asymptotic properties of the proposed recurrent neural networks for linear programming are analyzed theoretically, and the design principles for synthesizing the recurrent networks are discussed based on the results of analysis.
Scaling neural network for job-shop scheduling
41 Citations1990D.N. Zhou, Vladimir Cherkassky +2 more
The authors present a novel analog computational network for solving NP-complete constraint-satisfaction problems, i.e. job-shop scheduling, that uses linear cost functions and produces better solutions than the traveling-salesman-problem-type Hopfield approach and the integer linear programming approach.
Computers & Operations ResearchA connectionist approach to the quadratic assignment problem
36 Citations1992Jaishankar Chakrapani, Jadranka Skorin‐Kapov
The possibilities of applying a Boltzmann machine, and a related connectionist model in which the escape from local optima is performed in a deterministic way using tabu search, are tested for the quadratic assignment problem (QAP).
Computers & Operations ResearchA stochastic neural network for resource constrained scheduling
35 Citations1992Shivakumar Vaithyanathan, James P. Ignizio
This paper addresses the results obtained thus far in an ongoing research effort devoted to examination of the use of neural networks for the modeling and solution of one subclass of a particularly important category of problems: those of resource constrained scheduling.
Neural Information Processing SystemsBackpropagation and Its Application to Handwritten Signature Verification
35 Citations1988Timothy S. Wilkinson, Dorothy A. Mighell +1 more
A pool of handwritten signatures is used to train a neural network for the task of deciding whether or not a given signature is a forgery, and the best scores are on the order of 2% true signature rejection with 2-4% false signature acceptance.
Journal of Intelligent ManufacturingNeural computation for collision-free path planning
32 Citations1991Sukhan Lee, Jun Park
A massively parallel, connectionist algorithm for collision-free path planning based on representing a path as a series ofvia points or beads connected by elastic strings which are subject to displacement due to a potential field or a collision penalty function generated by polyhedral obstacles.
Contrasting neural nets with regression in predicting performance in the transportation industry
32 Citations2002Katherine A. Duliba
A neural network model was investigated as an alternative to regression and it was found that a neural net model outperformed the corresponding random effects specification, but did not perform as well as the fixed effects specification.
Detection of explosives in checked airline baggage using an artificial neural system
30 Citations1989Shea, Lin Lin
An artificial neural system (ANS) has been applied to the problem of discriminating between suitcases with and without explosives, and is shown to exceed the performance of the standard technique over a substantial range.
INFORMS Journal on ComputingNeural Networks for Selective Vehicle Routing Heuristics
26 Citations1990Kendall E. Nygard, Paul Juell +1 more
The system was very successful in identifying the optimal algorithm to apply to the new problems not used in training, and it is concluded that neural networks have considerable promise in the vehicle routing problem.
Neural NetworksLinear programming algorithm for neural networks
22 Citations1990John Shawe‐Taylor, Dave A. Cohen
A new learning algorithm for feedforward neural networks based on linear programming gives faster and more reliable learning on reasonably sized examples, and extensions of the method for efficient implementations in large networks are considered.
Expert Systems with ApplicationsA neural network approach to the classification problem
22 Citations1990James W. Denton, Ming S. Hung +1 more
The performance of a neural network as a classifier is evaluated and it is found that the performance of the neural network is comparable to the best of otheother methods under a wide variety of modeling assumptions.
Journal of Intelligent ManufacturingFunction-to-structure transformation in conceptual design: An associative memory-based paradigm
21 Citations1991Soundar Kumara, Sagar Kamarthi
The author models the human associative memory through artificial neural networks (ANN) with back-propagation with a different way of modeling the conceptual design phase using the paradigm of function-to-structure transformation.
Internet Archive (Internet Archive)The 1989 neuro-computing bibliography
19 Citations1989Casimir C. Klimasauskas
The burgeoning field of neurocomputing encompasses a diversity of fields, and its interdisciplinary nature, and the recent growth of neural networks as the sought after solution to difficult engineering problems in adaptive control, pattern recognition, and associative memories have created a real need.
Forecasting country risk ratings using a neural network
17 Citations2002Jean‐Claude Cosset, Jean‐Sébastien Roy
The performance of a neural network at predicting institutional investors' country risk ratings using eight economic indicators confirms the potential of the method for economic applications.
Journal of Intelligent ManufacturingDesign optimization with back-propagation neural networks
16 Citations1991Shou-Jen Lee, Henzer Chen
This paper demonstrates that the artificial neural nets technology provides a global perspective of the entire design space with good and near optimal solutions and can indeed be a potential technology for design optimization.
Journal of Intelligent ManufacturingIntegration of neurocomputing and system simulation for modeling continuous improvement systems in manufacturing
16 Citations1992Gregory R. Madey, Jay Weinroth +1 more
The use of a neural network embedded in a larger general-purpose simulation system (GPSS) simulation used to model continuous improvement systems (CIS) policies in a factory setting is described, used to accelerate the identification of an effective CIS policy by providing a more realistic simulation framework.
Synergy of artificial neural networks and knowledge-based expert systems for intelligent FMS scheduling
14 Citations1990Luis Rabelo, Sema Alptekin +1 more
A hybrid architecture that integrates artificial neural networks and knowledge-based expert systems to generate solutions for the real-time scheduling of flexible manufacturing systems is described, providing a system with a higher probability of success than traditional approaches.
IEEE Transactions on Systems Man and CyberneticsAn Empirical Test of New Forecasting Methods Derived from a Theory of Intelligence: The Prediction of Conflict in Latin America
13 Citations1978Paul J. Werbos, J. Titus
The compromise method is a new computer-based forecasting tool, available within the conversational CS package on the MIT Multics, and incorporates a new quasi-Newtonian method which can handle many parameters.
Time-table scheduling using neural network algorithms
13 Citations1990Tao-Chun Yu
A demonstration is presented of how to use neural network algorithms to schedule classes in an educational institute, basically a graph-coloring or graph-partitioning problem which belongs to the large class of NP (nondeterministic polynomial time)-complete problems, and it is difficult to solve.
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)Neural network models for Linear Programming
11 Citations1989J.C. Culioli, V. Protopopescu +2 more
A neural network that solves the general Linear Programming (LP) problem and proposes an approach based on Lagragrange multipliers that converges to primal and dual admissible solutions and shows that the duality gap can be rendered, in principle, as small as needed.
Possible applications of neural networks in manufacturing
10 Citations1989Dagli, Lammers
An approach that integrates artificial intelligence, operations research, and neural networks for the solution of a scheduling problem is examined.
Journal of Intelligent ManufacturingNeurally-inspired stochastic algorithm for determining multi-stage multi-attribute sampling inspection plans
10 Citations1991Jun Wang, Vira Chankong
A neurally-inspired approach to generating acceptance sampling inspection plans is proposed using a Bayesian cost model of multi-stage-multi-attribute sampling inspections for quality assurance in serial production systems.
A neural network nonlinear predictor
9 Citations1989Ukrainec, Haykin +1 more
It is demonstrated that a backpropagation neural network can be used for nonlinear time series prediction and improvements to the neural network structure with regard to the reduction of the observed performance deficit are discussed.
Neural network models of managerial judgment
8 Citations2002William Remus, Tim Hill
An experiment is presented which compares actual managerial decision-making, decisionsbased on neural network models, and decisions based on linear regression rules, and two level of environmental complexity.
ScholarSpace (University of Hawaii at Manoa)Function approximation using neural networks: a simulation study
7 Citations1992Leorey Marquez
This dissertation analyzes the effect of different characteristics of data on the training and estimation accuracy of neural networks and proposed enhancements to the neural network training procedure are proposed.
A neural network model for cell suppression of tabular data
4 Citations2003Lenore Desilets, Bruce Golden +2 more
The authors present a neural network model which seeks to learn which table entries to blank out to guarantee specified levels of protection in tabular formats and employs backpropagation.
Optimal task assignment using a neural network
3 Citations1989Toshiaki Tanaka, J.R. Canfield +2 more
By representing TAP in a more direct manner in the neural network, the need for constraints is eliminated, a valid solution is guaranteed, and the number of neurons and connections needed is reduced substantially.
Towards a stochastic neural model for combinatorial optimization
2 Citations1989de Carvalho, Barbosa
A stochastic neural model is proposed for the solution of hard combinatorial optimization problems, inspired by the Hopfield-Tank model and the Stochastic search ability of simulated annealing.
INFORMS Journal on ComputingA Neural Network Implementation of a Data Association Algorithm
2 Citations1990Allen L. Barker, Donald E. Brown +1 more
An algorithm for performing correspondence processing between the database reports and the new sensor reports to determine which pairs of sensor and database reports correspond to the same entity is presented.
Neural net implementation for assigning a product to a production line
2 Citations1989Roni Romano, Oded Maimon +1 more
A perceptron-type neural network is developed whose input parameters are a function of planning data, real-time status, and local expertise and its output is the foreman's decision.
Commodity trading with a two year old
1 Citations2002Joseph E. Collard
The back-propagation of errors algorithm was used to encode the relationship between the long/sell desired output and fundamental indicators plus technical variables into the ANN, which was able to predict long/short market positions for 5 months in the future.
…