Search Results for author: Peter Toth

Found 6 papers, 2 papers with code

Equivariant Hamiltonian Flows

no code implementations30 Sep 2019 Danilo Jimenez Rezende, Sébastien Racanière, Irina Higgins, Peter Toth

This paper introduces equivariant hamiltonian flows, a method for learning expressive densities that are invariant with respect to a known Lie-algebra of local symmetry transformations while providing an equivariant representation of the data.

Representation Learning

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.

Criticality & Deep Learning II: Momentum Renormalisation Group

no code implementations31 May 2017 Dan Oprisa, Peter Toth

Guided by critical systems found in nature we develop a novel mechanism consisting of inhomogeneous polynomial regularisation via which we can induce scale invariance in deep learning systems.

Criticality & Deep Learning I: Generally Weighted Nets

no code implementations26 Feb 2017 Dan Oprisa, Peter Toth

Motivated by the idea that criticality and universality of phase transitions might play a crucial role in achieving and sustaining learning and intelligent behaviour in biological and artificial networks, we analyse a theoretical and a pragmatic experimental set up for critical phenomena in deep learning.

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