Hava Siegelmann

Hava Siegelmann is a computer scientist at the University of Massachusetts and director of the school's Biologically Inspired Neural and Dynamical Systems Lab.^[1] In the early 1990s she proposed a new computational model, the Artificial Recurrent Neural Network (ARNN), and proved that it could perform beyond the Turing machine limit. This gave rise to her theory of Super-Turing Computation, which has stirred a whole new field in the computer science community and received much attention from the biological and philosophical communities as well.^[2] It was her PhD thesis and her subsequent 1995 paper in the Science magazine which she singly authored, where she coined the term Super-Turing, and started the new direction in computation, realization of organic life, and foundation for better Artificial Intelligence. Siegelmann is also one of the originators of the well-known Support Vector Clustering together with Vladimir Vapnik and colleagues. She further introduced the term dynamical health, meaning that in treating disorders, it is too limiting to seek only to repair primary causes of the disorder; any method of returning system dynamics to the balanced range, even under physiological challenges (e.g., by repairing the primary source, activating secondary pathways, or inserting specialized signaling), can ameliorate the system and be extremely beneficial to healing. Using this new concept she revealed the source of disturbance during shift work and travel leading to jet-lag and is currently studying human memory as well as cancer.

Biography

She earned her BA at Technion, her MSc at Hebrew University and her PhD at Rutgers University, all in Computer Science.^[3]

Her initial publications on the computational power of Neural Networks culminated in a sole-author paper in Science^[4][5] as well as monograph book on "Neural Networks and Analog Computation: Beyond the Turing Limit".

Publications

Papers

She has written over 50 refereed papers in professional journals including:

• W. Bush and H.T. Siegelmann,"Circadian Synchrony in Networks of Protein Rhythm Driven Neurons" Complexity 12, Issue 1 (Sept/Oct 2006)
• T. Leise and H Siegelmann, "Dynamics of a multistage circadian system," Journal of Biological Rhythms, August, 21:4 (2006), 314-323 - this attracted Media Attention e.g. Boston Globe, Yahoo!News, Forbes, United Press International, National Public Radio etc.
• A. Roitershtein, A. Ben-Hur and H.T. Siegelmann "On probabilistic analog automata," Theoretical Computer Science, 320(2-3) pp. 449–464, June 2004
• A. Ben-Hur, H.T. Siegelmann, "Computing with Gene Networks," Chaos 14(1) pp. 145–151, March 2004 (Work was chosen as the work to describe in physics news)
• A. Ben-Hur, J. Feinberg, S. Fishman and H. T. Siegelmann "Random matrix theory for the analysis of the performance of an analog computer: a scaling theory," Phys. Lett. A. 323(3-4) pp. 204–209, March 2004
• A. Ben-Hur, H.T. Siegelmann and S. Fishman. "A theory of complexity for continuous time dynamics." Journal of Complexity 18(1) : 51-86, 2002
• H.T. Siegelmann, "Neural and Super-Turing Computing," Philosophy 2002
• H.T. Siegelmann, "Analog Computational Power," Science, 271(19), January 1996: 373 - responding to comments on her earlier article
• H.T. Siegelmann, "Computation Beyond the Turing Limit," Science, 238(28), April 1995: 632-637
• H.T. Siegelmann and E.D. Sontag, "Analog Computation via Neural Networks," Theoretical Computer Science, 131, 1994: 331-360
• H.T. Siegelmann and E.D. Sontag, "Turing Computability with Neural Networks," Applied Mathematics Letters, 4(6), 1991: 77-80

and in addition given numerous invited lectures at conferences and research institutions.

Books

• Neural Networks and Analog Computation : Beyond the Turing Limit Birkhauser, Boston, December 1998 ISBN 0-8176-3949-7

She has contributed 18 book chapters including:

• "Neural Computing". New Trends in Computer Science, Gheroge Paul editor, 2003
• "Neural Automata and Computational Complexity," in Handbook of Brain Theory and Neural Networks, Michael A. Arbib (ed.), 2002
• "Finite vs. Infinite Descriptive Length in Neural Networks and the Associated Computational Complexity," in Finite vs. Infinite: Contributions to an Eternal Dilemma, C. Calude and Gh. Paun (eds.), Springer Verlag, 2000
• "Neural Automata and Computational Complexity," in Handbook of Brain Theory and Neural Networks, Michael A. Arbib (ed.), 2000
• "Computability with Neural Networks," in Lectures in Applied Mathematics, Vol. 32, J. Reneger, M. Shub, and S. Smale (eds.), American Mathematical Society, 1996: 733-747
• "Recurrent Neural Networks," in The 1000th Volume of Lecture Notes in Computer Science: Computer Science Today, Jan van Leeuwen (ed.), Springer Verlag, 1995: 29-45

Notes and references

1. ^ BINDS Lab
2. ^ Verifying Properties of Neural Networks
3. ^ Biography at UMass
4. ^ Siegelmann, H.T. (1995). "Computation beyond the Turing limit". Science 268 (5210): 545–548. doi:10.1126/science.268.5210.545. PMID 17756722. 
5. ^ Siegelmann, H.T. (1996). "Reply: Analog Computational Power". Science 271 (5247): 373. doi:10.1126/science.271.5247.373.