Uncertainty-guided Continual Learning with Bayesian Neural Networks Uncertainty-guided Continual Learning with Bayesian Neural Networks
Paper summary ## Introduction Bayesian Neural Networks (BNN): intrinsic importance model based on weight uncertainty; variational inference can approximate posterior distributions using Monte Carlo sampling for gradient estimation; acts like an ensemble method in that they reduce the prediction variance but only uses 2x the number of parameters. The idea is to use BNN's uncertainty to guide gradient descent to not update the important weight when learning new tasks. ## Bayes by Backprop (BBB): https://i.imgur.com/7o4gQMI.png Where $q(w|\theta)$ is our approximation of the posterior $p(w|x)$. $q$ is most probably gaussian with diagonal covariance. We can optimize this via the ELBO: https://i.imgur.com/OwGm20b.png ## Uncertainty-guided CL with BNN (UCB): UCB the regularizing is performed with the learning rate such that the learning rate of each parameter and hence its gradient update becomes a function of its importance. They set the importance to be inversely proportional to the standard deviation $\sigma$ of $q(w|\theta)$ Simply put, the more confident the posterior is about a certain weight, the less is this weight going to be updated. You can also use the importance for weight pruning (sort of a hard version of the first idea) ## Cartoon https://i.imgur.com/6Ld79BS.png
Uncertainty-guided Continual Learning with Bayesian Neural Networks
Ebrahimi, Sayna and Elhoseiny, Mohamed and Darrell, Trevor and Rohrbach, Marcus
arXiv e-Print archive - 2019 via Local Bibsonomy
Keywords: dblp

Summary by Massimo Caccia 1 year ago
Your comment:

ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and