Bayesian Regularization of Neural Networks

By Frank R. Burden, David A. Winkler. Artificial Neural Networks, 2009

633 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/7630724e68a1ea5a7d270eb4d3de53007f600bb6

How researchers see this paper

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

In Artificial Intelligence

1. Igor V. Tetko
2. Igor I. Baskin
3. Murat Kayri
4. David A. Winkler

In Control and Systems Engineering

1. Igor V. Tetko
2. Igor I. Baskin
3. Murat Kayri
4. David A. Winkler

In Materials Chemistry

1. Igor I. Baskin
2. David A. Winkler
3. Igor V. Tetko
4. Murat Kayri

Citations in the corpus

• A renaissance of neural networks in drug discovery (2016, methodology): “The overtraining problem can also be tackled using various regularization techniques, such as L1, L2, and max-norm [23] regularization with weights decay; Bayesian regularization [24 – 26]; or the dropout technique [27] suggested recently for deep learning (see below).”
• Predictive Abilities of Bayesian Regularization and Levenberg–Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data (2016, background): “01687 19 BRANNs have some important advantages, such as choice and robustness of model, choice of validation set, size of validation effort, and optimization of network architecture [13].”