Sciweavers

IDEAL
2005
Springer

Neural Networks: A Replacement for Gaussian Processes?

13 years 9 months ago
Neural Networks: A Replacement for Gaussian Processes?
Abstract. Gaussian processes have been favourably compared to backpropagation neural networks as a tool for regression. We show that a recurrent neural network can implement exact Gaussian process inference using only linear neurons that integrate their inputs over time, inhibitory recurrent connections, and one-shot Hebbian learning. The network amounts to a dynamical system which relaxes to the correct solution. We prove conditions for convergence, show how the system can act as its own teacher in order to produce rapid predictions, and comment on the biological plausibility of such a network.
Matthew Lilley, Marcus R. Frean
Added 27 Jun 2010
Updated 27 Jun 2010
Type Conference
Year 2005
Where IDEAL
Authors Matthew Lilley, Marcus R. Frean
Comments (0)