Eliezer said in one of this year’s interviews that gradient descent “knows” the derivative of the function it is trying to optimize whereas natural selection does not have access to that information—or is not equipped to exploit that information.
Maybe that clue will help you search for the answer to your question?
Eliezer said in one of this year’s interviews that gradient descent “knows” the derivative of the function it is trying to optimize whereas natural selection does not have access to that information—or is not equipped to exploit that information.
Maybe that clue will help you search for the answer to your question?