Abstract
The learning time of a simple neural network model is obtained through an
analytic computation of the eigenvalue spectrum for the Hessian matrix,
which describes the second order properties of the cost function in the
space of coupling coefficients. The form of the eigenvalue distribution
suggests new techniques for accelerating the learning process, and provides
a theoretical justification for the choice of centered versus biased state
variables.
Original language | American English |
---|---|
Pages (from-to) | 918-924 |
Journal | Advances in Neural Information Processing Systems |
Volume | 3 |
State | Published - 1991 |