University Wins 10th Patent for Machine Learning Invention
Posted: March 12, 2003 at 1:00 am, Last Updated: November 30, -0001 at 12:00 am
By Robin Herron
George Mason has achieved a milestone with its 10th patent, issued Feb. 18, for an invention by Ryszard Michalski in the School of Computational Sciences.
Michalski, the Planning Research Corporation Professor of Computational Sciences and director of the Machine Learning and Inference Laboratory, earned the first patent for his school with Learnable Non-Darwinian Evolution Model (LEM), a new form of evolutionary computation. Unlike traditional evolutionary computation that is based on non-directed evolution, LEM is a model of evolutionary processes directed by artificial intelligence.
In LEM, instead of letting the computer make random mutations and recombinations to create new individuals as in Darwinian evolutionary computation, the system tries to make the “right” ones. Guided by machine learning at each stage, the system creates a theory of “good” direction of evolution, Michalski says. Subsequently, it uses this theory to generate new individuals for the next generation.
Michalski and his graduate students, Janusz Wojtusiak, Ying Cao, and Guido Cervone, continue research on LEM under National Science Foundation funding. He says the LEM idea provides “so many new research opportunities that they may occupy me for the rest of my life.”
Recently, a research group at Utah State University has undertaken efforts to implement LEM as a hardware system, and plans to use it to “grow artificial brains.”