Steve Omohundro

American scientist
The basics

Quick Facts

IntroAmerican scientist
PlacesUnited States of America
isComputer scientist
Work fieldTechnology Science
Gender
Male
The details

Biography

Stephen M. Omohundro (born 1959) is an American scientist known for his research on Hamiltonian physics, dynamical systems, programming languages, machine learning, machine vision, and the social implications of artificial intelligence. His current work uses rational economics to develop safe and beneficial intelligent technologies for better collaborative modeling, understanding, innovation, and decision making.

Education

Omohundro earned degrees in physics and mathematics from Stanford University and a Ph.D. in physics from the University of California, Berkeley.

Learning algorithms

Efficient geometric learning algorithms

Omohundro started the "Vision and Learning Group" at the University of Illinois which produced 4 Masters and 2 Ph.D. theses. He developed a number of efficient geometric algorithms for speeding up neural network, machine learning, machine vision, and graphics tasks, several of which are widely used. Omohundro created numerous algorithms based on k-d trees, invented the powerful balltree and boxtree geometric data structures., and invented the powerful bumptree structure, which dramatically speeds up Gaussian mixture based neural network algorithms and produced a factor of 50 speedup on a robotics task.

Manifold learning and lipreading

Omohundro invented the general and widely used manifold learning task and introduced several algorithms for accomplishing this task. Omohundro, Chris Bregler and others extended these ideas and applied them to a wide range of visual learning and modelling tasks.

Model merging and grammar learning

Omohundro invented the Best-first model merging approach to machine learning. Omohundro and Andreas Stolcke applied this model to learning stochastic grammars. Their approach was very successful in learning Hidden Markov Models and Stochastic Context-free Grammars and is now widely used.

Family Discovery Learning Algorithm

Steve Omohundro

Omohundro developed the Family Discovery Learning Algorithm, which discovers the dimension and structure of a parameterized family of stochastic models.

Self-improving artificial lntelligence and AI safety

Omohundro started Self-Aware Systems in Palo Alto, California to research the technology and social implications of self-improving artificial intelligence. He is an advisor to the Machine Intelligence Research Institute on artificial intelligence. He argues that rational systems exhibit problematic natural "drives" that will need to be countered in order to build intelligent systems safely. His papers, talks, and videos on AI safety have generated extensive interest. He has given many talks on self-improving artificial intelligence, cooperative technology, AI safety, and connections with biological intelligence.

Programming languages

*Lisp parallel programming language

At Thinking Machines Corporation, Cliff Lasser and Steve Omohundro developed Star Lisp, the first programming language for the Connection Machine. Omohundro also helped create the data parallel style of parallel programming and developed many parallel algorithm libraries and applications for the Connection Machine.

Sather programming language

Omohundro joined the International Computer Science Institute (ICSI) in Berkeley, California, where he led the development of the open source programming language Sather, which introduced a number of advances in object-oriented language design. Sather is featured in O'Reilly's History of Programming Languages poster.

Physics and dynamical systems theory

Omohundro's book Geometric Perturbation Theory in Physics describes natural Hamiltonian symplectic structures for a wide range of physical models that arise from perturbation theory analyses.

He showed that there exist smooth partial differential equations which stably perform universal computation by simulating arbitrary cellular automata. The asymptotic behavior of these PDEs is therefore logically undecidable.

With John David Crawford he showed that the orbits of three-dimensional period doubling systems can form an infinite number of topologically distinct torus knots and described the structure of their stable and unstable manifolds.

Other contributions

Mathematica and Apple tablet contest

From 1986 to 1988, he was an Assistant Professor of Computer science at the University of Illinois at Urbana-Champaign and cofounded the Center for Complex Systems Research with Stephen Wolfram and Norman Packard. While at the University of Illinois, he worked with Stephen Wolfram and others (D. Grayson, R. Maeder, H. Cejtin, D. Ballman and J. Keiper) to create the symbolic mathematics program Mathematica. He and Stephen Wolfram led a team of students that won an Apple Computer contest to design "The Computer of the Year 2000." Their design entry "Tablet" was a touchscreen tablet with GPS and other features that finally appeared when the Apple iPad was introduced 22 years later.

Neural models of attention

Subutai Ahmad and Steve Omohundro developed biologically realistic neural models of selective attention.

Bayesian image database search

Omohundro became a Research scientist at the NEC Research Institute, working on machine learning and computer vision, and was a co-inventor of U.S. Patent 5,696,964, "Multimedia Database Retrieval System Which Maintains a Posterior Probability Distribution that Each Item in the Database is a Target of a Search."

Pirate puzzle

Omohundro developed an intriguing extension to the game theoretic pirate puzzle that was featured in Scientific American.

Gesture-based user interfaces

Omohundro and 5 others invented U.S. Patent 7,775,439 B2 "Featured Wands for Camera Calibration and as a Gesture Based 3D Interface Device."

Publications

  • Christoph Bregler, Stephen Omohundro, Michelle Covell, Malcolm Slaney, Subutai Ahmad, David Forsyth, Jerry Feldman, "Probabilistic Models of Verbal and Body Gestures" in Computer Vision in Man-Machine Interfaces, eds. R. Cipolla and A. Pentland, Cambridge University Press, 1998.
  • Christoph Bregler and Stephen M. Omohundro, "Learning Visual Motion Models for Lip Reading" in Motion-Based Recognition, eds. M. Sha and R. Jain, Kluwer Academic Press, 1997.
  • Stephen M. Omohundro, "Family Discovery", in Advances in Neural Information Processing Systems 8, eds. D. S. Touretzky, M. C. Mozer and M. E. Hasselmo, MIT Press, Cambridge, MA, 1996.
  • Christoph Bregler and Stephen M. Omohundro, "Surface Learning with Applications to Lipreading", in Cowan, J. D., Tesauro, G., and Alspector, J., (eds.) Advances in Neural Information Processing Systems 6, Morgan Kaufmann Publishers, San Francisco, CA, 1994
  • Stephen M. Omohundro, "The Sather Programming Language", Dr. Dobb's Journal, Volume 18, Issue 11, October 1993, p. 42.
  • Stephen M. Omohundro, "Geometric Learning Algorithms" Physica D, 42 (1990) 307-321
  • Stephen M. Omohundro, "Modelling Cellular Automata with Partial Differential Equations", Physica D, 10D (1984) 128-134
  • Stephen M. Omohundro, "Autonomous technology and the greater human good", Journal of Experimental and Theoretical Artificial Intelligence, Published online: 10 Apr 2014. This paper has become the most downloaded paper in the journal.

The contents of this page are sourced from Wikipedia article. The contents are available under the CC BY-SA 4.0 license.