Search Results for author: Agnieszka Grabska-Barwinska

Found 8 papers, 3 papers with code

Gated Linear Networks

1 code implementation30 Sep 2019 Joel Veness, Tor Lattimore, David Budden, Avishkar Bhoopchand, Christopher Mattern, Agnieszka Grabska-Barwinska, Eren Sezener, Jianan Wang, Peter Toth, Simon Schmitt, Marcus Hutter

This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs).

Progress & Compress: A scalable framework for continual learning

no code implementations ICML 2018 Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell

This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task.

Active Learning Atari Games +1

Online Learning with Gated Linear Networks

no code implementations5 Dec 2017 Joel Veness, Tor Lattimore, Avishkar Bhoopchand, Agnieszka Grabska-Barwinska, Christopher Mattern, Peter Toth

This paper describes a family of probabilistic architectures designed for online learning under the logarithmic loss.

Optimal prior-dependent neural population codes under shared input noise

no code implementations NeurIPS 2014 Agnieszka Grabska-Barwinska, Jonathan W. Pillow

The brain uses population codes to form distributed, noise-tolerant representations of sensory and motor variables.

Cannot find the paper you are looking for? You can Submit a new open access paper.