English

Deep Prior

Machine Learning 2017-12-19 v2 Machine Learning

Abstract

The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as images or sounds. In this work we investigate the possibility of learning the prior distribution over neural network parameters using such tools. Our resulting variational Bayes algorithm generalizes well to new tasks, even when very few training examples are provided. Furthermore, this learned prior allows the model to extrapolate correctly far from a given task's training data on a meta-dataset of periodic signals.

Keywords

Cite

@article{arxiv.1712.05016,
  title  = {Deep Prior},
  author = {Alexandre Lacoste and Thomas Boquet and Negar Rostamzadeh and Boris Oreshkin and Wonchang Chung and David Krueger},
  journal= {arXiv preprint arXiv:1712.05016},
  year   = {2017}
}

Comments

Workshop paper, Accepted at Bayesian Deep Learning workshop, NIPS 2017

R2 v1 2026-06-22T23:17:31.471Z