Riemannian metrics for neural networks I: feedforward networks

03/04/2013
by   Yann Ollivier, et al.
0

We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradient using the Fisher information matrix, or on Hessian methods, scaled down in a specific way to allow for scalability while keeping some of their key mathematical properties.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset