Artificial Neuronal Ensembles with Learned Context Dependent Gating

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.

Continual Learning Permuted-MNIST +1

Learning Deep Generative Models with Annealed Importance Sampling

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.

Variational Inference

Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization

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.