The Applicability of Neural Nets for Decision Support

The aim of this paper is to discuss the possible role of neural nets for decision support. The discussion will be conducted along two connected lines. The first line regards the possibilities to solve combinatorial optimization problems with multi-layered perceptrons. Particular attention is paid to the required complexity of such neural nets. The second line regards the use of neural nets as a kind of black-box decision mechanism for decision problems for which the underlying processes are difficult or even not well understood. For direct use of the results of the first line it would be essential to have cheap neuro-based computing aids available. However, even without the availability of such aids, the results are useful for supporting the second line. The second line itself has its value independent of the availability of special neural computing aids. Its essence is that it provides an alternative paradigm for decision support, which can also be simulated on traditional computing equipment.

[1]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[2]  Emile H. L. Aarts,et al.  The construction of minimal multilayered perceptrons: A case study for sorting , 1993, Neurocomputing.

[3]  Albert P. M. Wagelmans,et al.  Economic Lot Sizing: An O(n log n) Algorithm That Runs in Linear Time in the Wagner-Whitin Case , 1992, Oper. Res..

[4]  G. Bitran,et al.  Computational Complexity of the Capacitated Lot Size Problem , 1982 .

[5]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[6]  E. J. Anderson,et al.  Deterministic Lotsizing Models for Production Planning , 1991 .

[7]  Emile H. L. Aarts,et al.  The Minimal Number of Layers of a Perceptron That Sorts , 1994, J. Parallel Distributed Comput..

[8]  James R. Evans.  An efficient implementation of the Wagner-Whitin algorithm for dynamic lot-sizing , 1985 .

[9]  J. K. Lenstra,et al.  Deterministic Production Planning: Algorithms and Complexity , 1980 .

[10]  Emile H. L. Aarts,et al.  The Design and Complexity of Exact Multilayered Perceptrons , 1991, Int. J. Neural Syst..

[11]  Franco P. Preparata,et al.  New Parallel-Sorting Schemes , 1978, IEEE Transactions on Computers.

[12]  Ehl Emile Aarts,et al.  Neural networks and production planning , 1991 .

[13]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[14]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[15]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[16]  J Jaap Wessels,et al.  Multi item lot size determination and scheduling under capacity constraints , 1976 .

[17]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[18]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[19]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[20]  G. A. P. Kindervater.  Exercises in parallel combinatorial computing , 1991 .

[21]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[22]  George Cybenko,et al.  Complexity Theory of Neural Networks and Classification Problems , 1990, EURASIP Workshop.

[23]  Ehl Emile Aarts,et al.  The classification capabilities of exact two-layered perceptrons , 1991 .

[24]  Wen-Tsuen Chen,et al.  A neural sorting network with O(1) time complexity , 1990, IJCNN.