About This Blog

Automating Invention is Robert Plotkin's blog on the impact of computer-automated inventing on the future of invention and patent law.

Click here for latest videos.

News Feeds

« Simulating Auto Assembly | Main | Easing the Patent Processing Bottleneck »

May 19, 2009

Automating the Work of Scientists

We wrote here in an earlier post about a robot in the U.K. that can perform laboratory experiments independently ("Meet Adam, the Robotic Junior Lab Assistant"). Now the journal Science reports that two Cornell scientists have developed a computer program that sifts raw data to uncover fundamental laws of nature.

The program, developed by professor Hod Lipson and graduate student Michael Schmidt, uses genetic programming techniques by starting with random guesses at a solution and then using an evolutionary algorithm to mutate equations until it finds a solution that works. The research worked on data to find invariant equations. Such equations often point to fundamental natural laws.

"It's a nice piece of work," said John R. Koza, a computer scientist at Stanford who pioneered genetic programming. "It's another good example of how genetic programming can do things that are comparable to what human scientists can do."

See video of Hod Lipson and his self-replicating robots on TED.com.

Posted by BlogAuthor1 at May 19, 2009 1:11 AM
category: Artificial Invention


Post a comment

Thanks for signing in, . Now you can comment. (sign out)

(If you haven't left a comment here before, you may need to be approved by the site owner before your comment will appear. Until then, it won't appear on the entry. Thanks for waiting.)

Remember me?