Robust Artificial Neural Network Architectures

Many artificial intelligence (AI) techniques are inspired by problem-solving strategies found in nature. Robustness is a key feature in many natural systems. This paper studies robustness in artificial neural networks (ANNs) and proposes several novel, nature inspired ANN architectures. The paper includes encouraging results from experimental studies on these networks showing increased robustness.

Authors:

• A. Schuster

Keywords:

• robustness
• robust artificial neural networks architectures.

References:

[1] A.L. Barab'asi and E. Bonabeau, "Scale-free networks," Scientific American,
vol. 288, pp. 55-59, May 2003.
[2] P. Bentley, "Investigations into graceful degradation of evolutionary
developmental software," Natural Computing, vol. 4, pp. 417-437, 2005.
[3] H. Brighton and H. Selina, Introducing Artificial Intelligence. Icon Books
UK, 2003.
[4] D. Dvorak, G. Bollella, T. Canham, V. Carson, V. Champlin, B. Giovannoni,
M. Indictor, K. Meyer, A. Murray, and K. Reinholtz, "Project
golden gate: Towards real-time Java in space missions," in Proc. 7th
IEEE International Symposium on Object-Oriented Real-Time Distributed
Computing (ISORC 2004), IEEE Computer Society, Vienna, Austria,
2004, pp. 15-22.
[5] B. Hayes, "Ode to the code," American Scientist, vol. 92, pp. 494-498,
November-December 2004.
[6] M.N. Huhns and V.T. Holderfield, "Robust software," IEEE Internet
Computing, vol. 6:2, pp. 80-82, March-April 2002.
[7] D. Jackson, "Dependable software by design," Scientific American, vol.
294, pp. 58-65, June 2006.
[8] G.A. Jones and M.J. Jones, Information and Coding Theory. Springer
Verlag London, 2000.
[9] K. Mehrotra, C.K. Monan, S. and Ranka, Elements of Artificial Neural
Networks. The MIT Press, 1997.
[10] R. Pfeifer, "Embodied artificial intelligence: trends and challenges,"
in Embodied Artificial Intelligence, Lecture Notes in Computer Science
LNCS, vol. 3139, F. Iida, R. Pfeifer, L. Steels, and Y. Kuniyoshi, Eds.
Springer-Verlag Berlin, Heidelberg, New York, 2003, pp. 1-26.
[11] A. Schuster, "A hybrid robot control system based on soft computing
techniques," in Advances in Applied Artificial Intelligence, Lecture Notes
in Artificial Intelligence LNAI, vol. 4031, A. Moonis and D. Richard Eds.
Springer Verlag, Berlin, Heidelberg, New York, 2006, pp. 187-196.