PubMed · 17117493
Implementing Gaussian process inference with neural networks.
Abstract
Gaussian processes compare favourably with backpropagation neural networks as a tool for regression, and Bayesian neural networks have Gaussian process behaviour when the number of hidden neurons tends to infinity. We describe a simple recurrent neural network with connection weights trained by one-shot Hebbian learning. This network amounts to a dynamical system which relaxes to a stable state in which it generates predictions identical to those of Gaussian process regression. In effect an infinite number of hidden units in a feed-forward architecture can be replaced by a merely finite number, together with recurrent connections.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Marcus Frean, Matt Lilley, Phillip Boyle. 2006. Implementing Gaussian process inference with neural networks.. https://doi.org/10.1142/s012906570600072x. https://pubmed.health/record/pubmed%3A17117493/implementing-gaussian-process-inference-with-neural-networks
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite PubMed Health by Indiciae: BibTeX · RIS.