Steve Omohundro

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.

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

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.

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.

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.

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

...
Wikipedia