Correspondence between neuroevolution and gradient descent.

Abstract excerpt

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the learning process, neuroevolution is equivalent to gradient descent on the loss function. We use numerical simulation to...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Algorithms
• Share to Computer Simulation
• Share to Mutation