Lipson has been involved with machine learning and presented his "self-aware" robot at the 2007 TED conference.[6]
Beginning in 2009, he and his Cornell University graduate student Michael Schmidt developed a software named Eureqa[7] capable of deriving equations, mathematical relationships and laws of nature from sets of data: for instance, deriving Newton's second law of motion from a data set of positions and velocities of a double pendulum.[8][9] In 2011, it was reported that Eureqa had succeeded at a much more complex task: re-deriving seven equations describing how levels of various chemical compounds fluctuate in oxygen-deprived yeast cells.[10]
In research on robotic self-awareness he advocates "self-simulation" as preliminary stage.[11]
Lipson has been involved with teams that have created a number of machines including:
[[[Category:All articles with dead external links]][dead link] Live broadcast of Hod Lipson on The Agenda with Steve Paikin discussion panel, "Robotics Revolution and the Future of Evolution"] with Cory Doctorow, Michael Belfiore, and Eliezer Yudkowsky at the Quantum to Cosmos festival.