Neural networks: A replacement for Gaussian processes?

Gaussian processes have been favourably compared to back-propagation 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.