1 code implementation • 17 Jan 2023 • Matthew J. Tilley, Michelle Miller, David J. Freedman
Finally, there is a regularization term responsible for ensuring that new tasks are encoded in gates that are as orthogonal as possible from previously used ones.
1 code implementation • 12 Jun 2019 • Xinqiang Ding, David J. Freedman
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are two main approximate approaches for learning deep generative models by maximizing marginal likelihood.
3 code implementations • 2 Feb 2018 • Nicolas Y. Masse, Gregory D. Grant, David J. Freedman
Several recent studies have proposed methods to stabilize connection weights of ANNs that are deemed most important for solving a task, which helps alleviate catastrophic forgetting.