HYPERPARAMETERS: OPTIMIZE, OR INTEGRATE OUT?

By David John Cameron MacKay. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Felix Laumann
2. Kumar Shridhar
3. Marcus Liwicki
4. Michael Hirsch
5. Alex Graves
6. J. Urgen Schmidhuber
7. Yoshua Bengio
8. Trevor Darrell

Citations in the corpus

• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference (2019, methodology): “A Bayesian approach to Neural Networks provides the shortcomings with the backpropagation approach [45] as Bayesian methods naturally account for uncertainty in parameter estimates and can propagate this uncertainty into predictions.”
• Blind deconvolution in scientific imaging & computational photography (2011, background): “Richardson (1972) and Lucy (1974), which date back to the early 70s.”