On a new episode of ID the Future, CSC Director of Communications Rob Crowther talks with Robert Marks, Distinguished Professor of Electrical and Computer Engineering at Baylor University, about Marks’s new book, Introduction to Evolutionary Informatics, which makes an important but esoteric-sounding field accessible to the general reader.
Dr. Marks talks about how he and William Dembski originally connected as researchers, and began working on the subject in 2007, how intelligent design can inform thinking on artificial intelligence, and what a “search for a search” means in evolutionary terms. More.
Needle-in-the-haystack problems look for small targets in large spaces. In such cases, blind search stands no hope of success. Conservation of information dictates any search technique will work, on average, as well as blind search. Success requires an assisted search. But whence the assistance required for a search to be successful? To pose the question this way suggests that successful searches do not emerge spontaneosly but need themselves to be discovered via a search. The question then naturally arises whether such a higher-level “search for a search” is any easier than the original search. We prove two results: (1) The Horizontal No Free Lunch Theorem, which shows that average relative performance of searches never exceeds unassisted or blind searches, and (2) The Vertical No Free Lunch Theorem, which shows that the difficulty of searching for a successful search increases exponentially with respect to the minimum allowable active information being sought.
See also: Google’s AI guru says AI must build on human intelligence
Information theory is bad news for Darwin: Evolutionary informatics takes off