Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes

Research output: Contribution to journalArticle


We extend feed-forward neural networks with a Dirichlet process prior over the weight distribution. This enforces a sharing on the network weights, which can reduce the overall number of parameters drastically. We alternately sample from the posterior of the weights and the posterior of assignments of network connections to the weights. This results in a weight sharing that is adopted to the given data. In order to make the procedure feasible, we present several techniques to reduce the computational burden. Experiments show that our approach mostly outperforms models with random weight sharing. Our model is capable of reducing the memory footprint substantially while maintaining a good performance compared to neural networks without weight sharing.

Original languageEnglish
Article number42(1)
Pages (from-to)246-252
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Publication statusE-pub ahead of print - 6 Dec 2018


  • Bayesian neural networks
  • Dirichlet processes
  • Gibbs sampling
  • hybrid Monte-Carlo
  • non-conjugate models
  • weight sharing

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes'. Together they form a unique fingerprint.

Cite this