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

GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability

Lengyel, D; Petangoda, JC; Falk, I; Highnam, K; Lazarou, M; Kolbeinsson, A; Deisenroth, MP; (2020) GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability. arXiv: Ithaca, NY, USA. Green open access

[thumbnail of 2011.07407v1.pdf]
Preview
Text
2011.07407v1.pdf - Accepted version

Download (2MB) | Preview

Abstract

We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produce the same input-output map. Our proposed method, GENNI, allows us to efficiently identify parameters that are functionally equivalent and then visualise the subspace of the resulting equivalence class. By doing so, we are now able to better explore questions surrounding identifiability, with applications to optimisation and generalizability, for commonly used or newly developed neural network architectures

Type: Working / discussion paper
Title: GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
Open access status: An open access version is available from UCL Discovery
Publisher version: https://arxiv.org/abs/2011.07407v1
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
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
URI: https://discovery.ucl.ac.uk/id/eprint/10117305
Downloads since deposit
8Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item