GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability

MaRDI QIDQ6353752zbMATH OpenFDO

Authors Daniel Lengyel, Janith Petangoda, Isak Falk, Kate Highnam, Michalis Lazarou, Arinbjorn Kolbeinsson, Marc Peter Deisenroth, Nicholas R. Jennings

Publication date 14 November 2020

Has companion code repository https://github.com/Do-Not-Circulate/GENNI

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.

This page was built for publication: GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353752)