Timezone: »

 
Poster
Gaussian Gated Linear Networks
David Budden · Adam Marblestone · Eren Sezener · Tor Lattimore · Gregory Wayne · Joel Veness

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #380
in Poster Session 2 »

We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using backpropagation to learn features, GLNs have a distributed and local credit assignment mechanism based on optimizing a convex objective. This gives rise to many desirable properties including universality, data-efficient online learning, trivial interpretability and robustness to catastrophic forgetting. We extend the GLN framework from classification to multiple regression and density modelling by generalizing geometric mixing to a product of Gaussian densities. The G-GLN achieves competitive or state-of-the-art performance on several univariate and multivariate regression benchmarks, and we demonstrate its applicability to practical tasks including online contextual bandits and density estimation via denoising.

Author Information

David Budden (DeepMind)
Adam Marblestone
Eren Sezener (DeepMind)
Tor Lattimore (DeepMind)
Gregory Wayne (Google DeepMind)
Joel Veness (Deepmind)

More from the Same Authors