UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Compact neural networks based on the multiscale entanglement renormalization Ansatz

Hallam, A; Grant, E; Stojevic, V; Severini, S; Green, AG; (2018) Compact neural networks based on the multiscale entanglement renormalization Ansatz. In: British Machine Vision Conference 2018, BMVC 2018. BMVC: Newcastle-upon-Tyne, UK. Green open access

[img]
Preview
Text
0784.pdf - Published version

Download (230kB) | Preview

Abstract

This paper demonstrates a method for tensorizing neural networks based upon an efficient way of approximating scale invariant quantum states, the Multi-scale Entanglement Renormalization Ansatz (MERA). We employ MERA as a replacement for the fully connected layers in a convolutional neural network and test this implementation on the CIFAR-10 and CIFAR-100 datasets. The proposed method outperforms factorization using tensor trains, providing greater compression for the same level of accuracy and greater accuracy for the same level of compression. We demonstrate MERA layers with 14000 times fewer parameters and a reduction in accuracy of less than 1% compared to the equivalent fully connected layers, scaling like O(N).

Type: Proceedings paper
Title: Compact neural networks based on the multiscale entanglement renormalization Ansatz
Event: BMVC 2018 - 29TH British Machine Vision Conference
Open access status: An open access version is available from UCL Discovery
Publisher version: http://bmvc2018.org/programmedetail.html
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > London Centre for Nanotechnology
URI: https://discovery.ucl.ac.uk/id/eprint/10082844
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item