scholarly journals Neural Networks: A Replacement for Gaussian Processes?

2005 ◽  
pp. 195-202 ◽  
Author(s):  
Matthew Lilley ◽  
Marcus Frean
Keyword(s):  
Neural Networks ◽  
Gaussian Processes

Computation with Infinite Neural Networks

1998 ◽  
Vol 10 (5) ◽  
pp. 1203-1216 ◽  
Author(s):  
Christopher K. I. Williams
Keyword(s):  
Neural Networks ◽  
Gaussian Process ◽  
Infinite Number ◽  
Wide Class ◽  
Gaussian Processes ◽  
Covariance Function ◽  
Bayesian Prediction ◽  
Infinite Networks

For neural networks with a wide class of weight priors, it can be shown that in the limit of an infinite number of hidden units, the prior over functions tends to a gaussian process. In this article, analytic forms are derived for the covariance function of the gaussian processes corresponding to networks with sigmoidal and gaussian hidden units. This allows predictions to be made efficiently using networks with an infinite number of hidden units and shows, somewhat paradoxically, that it may be easier to carry out Bayesian prediction with infinite networks rather than finite ones.

scholarly journals On the expected behaviour of noise regularised deep neural networks as Gaussian processes

2020 ◽  
Vol 138 ◽  
pp. 75-81
Author(s):  
Arnu Pretorius ◽  
Herman Kamper ◽  
Steve Kroon
Keyword(s):  
Neural Networks ◽  
Gaussian Processes ◽  
Deep Neural Networks

Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

2015 ◽  
Author(s):  
Tamás Grósz ◽  
Róbert Busa-Fekete ◽  
Gábor Gosztolya ◽  
László Tóth
Keyword(s):  
Neural Networks ◽  
Gaussian Processes
Sign in / Sign up

Export Citation Format

Share Document