Abstract | ||
---|---|---|
•A novel Bayesian neural net construction allowing closed-form variational inference.•Closed-form updates are made tractable by decomposing ReLU into two components.•The resulting inference scheme fast convergence, compatible for online learning.•State-of-the-art learning curve when applied to Bayesian active learning.•Outperforms deterministic neural nets in scarce data regimes. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.patrec.2018.07.001 | Pattern Recognition Letters |
Keywords | Field | DocType |
Bayesian Neural Networks,Variational Bayes,Online learning,Active learning | Small data,Active learning,Pattern recognition,Inference,Artificial intelligence,Expectation propagation,Deep learning,Artificial neural network,Mathematics,Bayesian probability,Bayes' theorem | Journal |
Volume | ISSN | Citations |
112 | 0167-8655 | 0 |
PageRank | References | Authors |
0.34 | 16 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Melih Kandemir | 1 | 182 | 16.91 |