Cascaded VLSI neural network chips: Hardware learning for pattern recognition and classification

Abstract

Currently map data is stored as high- resolution digitized pixel data on CD-ROM storage devices. The copious amount of data generated from the global map data base overwhelms even high-density optical storage methods. In addition, the map user is concerned not with the high-resolution image of the map, but the actual features such as roads and rivers. By classifying the map-image pixels into separate features, the dimensional ity of the data is dramatically reduced, the map is significantly decluttered, and the data is in the form most suitable for further analysis. Because of the extensive volume of the data already stored and its on-demand nature, classification speed must exceed the CD-ROM read speed so that access rates are unaffected. This paper describes a neural network approach to pattern classification applied to map pixel data. Software simulations of a sophisticated neural network show that neural networks are indeed equivalent to optimal statistical pattern classifiers. Furthermore, a fully parallel neural network hardware implementatiort developed at JPL, surpasses the necessary processing speed, and provides high classification accuracy. Our software as well a hardware results are presented in this paper along with a brief backgrourtd in pattern classification and neural networks.

Keywords

map data map-image pixels neural network pattern classification

Get full access to this article

View all access options for this article.

References

Blum, A. , Rivest, R.L. , 1989, "Training a 3-node neural network is NP-Complete , ed. Touretzky, D. S. , Advances in Neural Information Processing Systems I, Morgan Kaufman Pub., San Mateo, CA, pp. 494-501.

Duda R.O. , and Hart P.E. , 1973, Pattern Classification and Scene Analysis, Wiley, New York.

Duong, T. , Eberhardt, S.P. , Tran, M. , Daud, T. , Thakoor, A.P. 1992, "Learning and optimization with cascadedVLSI neural network building-block chips," Submitted to the International Joint Conference on Neural Networks.

Fahlman, S.E. , Lebiere, C. , 1990, "The cascadecorrelation learning architecture," in Advances in Neural Information Processing Systems II, ed. Touretzky, D. , Morgan Kaufman, San Mateo, CA. pp. 524-532.

Hinton, G.E. , Sejnowski, T.J. , 1986, "Learning and relearning in Boltzmann machines," ed. Rumelhart, D. E. , McClelland, J. L. , Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations, MIT Press, Cambridge, MA, Chapter 7.

Hoehfield, M. , Fahlman, S.E. , "Learning with limited numerical precision using the Cascade-Correlation algorithm," To be published in IEEE Transactions on Neural Networks.

Hollis, P.W. , Harper, J.S. , Paulos , J.J. , 1990, " The effects of precision constraints in a back-propagation learning network ," Neural Computation 2, pp. 363-373.

Judd, J.S. , 1990, Neural Network Design and the Complexity of Learning , MIT Press, Cambridge, MA.

Knerr, S. Personnaz, L. Dreyfus, G. 1991 "A new approach to the design of neural network classifiers and its application to the automatic recognition of handwritten digits," Proceedings International Joint Conference on Neura l Networks, July 8-12, Seattle, WA, pp. 91-96.

10.

Lee, Y. , Lippman R.P. , 1990, "Practical characteristics of neural networks and conventional pattern classifiers on artificial and speech problems," in Advances in Neural Information Processing Systems II, ed. Touretzky, D. Morgan Kaufman, San Mateo, CA. pp. 168-177.

11.

Miller, J.W. , Goodman, R. , Smyth , P. , 1991 " Objective functions for probability estimation," Proceedings International Joint Conference on Neural Networks, July 8-12, Seattle, WA, pp. 881-886.

12.

Rumelhart, D.E. , Hinton, G.E. , Williams , R.J. , 1986, " Learning internal representations by error propagation," ed. Rumelhart, D.E. , McClelland, J.L. , Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1:Foundations, MIT Press, Cambridge, MA. Chapter 8.

13.

Rumelhart, D.E. , McClelland , J.L. , 1986 Parallel Distributed Processing: Explorations in the Microstructure of Cognition . Volume 1:Foundations, MIT Press, Cambridge, MA.