Correspondence between neuroevolution and gradient descent.
Nat Commun
; 12(1): 6317, 2021 11 02.
Article
in En
| MEDLINE
| ID: mdl-34728632
ABSTRACT
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 show that this correspondence can be observed for finite mutations, for shallow and deep neural networks. Our results provide a connection between two families of neural-network training methods that are usually considered to be fundamentally different.
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Algorithms
/
Neural Networks, Computer
/
Mutation
Language:
En
Journal:
Nat Commun
Journal subject:
BIOLOGIA
/
CIENCIA
Year:
2021
Document type:
Article
Affiliation country: