Akin to genetic algorithms, which we experimented with, but found that the combinatorics (very large number of solutions) of real world problems were too large or unstable for us to practically use. I can see the similarities to what is presented here, so worth following. Though would seem to have the same issues. A move towards the automation of AI approaches. Technical.
AI Is Evolving All by Itself
in Science
By Edd Gent
Google's Quoc Le and colleagues have designed a program that borrows concepts from Darwinian evolution, including survival of the fittest, to assemble artificial intelligence (AI) that generationally improves with effectively no human input. The AutoML-Zero program generates 100 candidate algorithms by randomly combining mathematical operations, then tests them on a simple task, like an image-recognition problem. AutoML-Zero compares the algorithms' performance to that of hand-designed algorithms, with copies of top-performing algorithms mutated by randomly replacing, editing, or deleting some of their code to create variations; these ‘offspring’ are added to the population while older algorithms are removed. AutoML-Zero was able to reproduce decades of AI research in days. Le said, "Our ultimate goal is to actually develop novel machine learning concepts that even researchers could not find." ... "
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment