GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
From MaRDI portal
Publication:6353752
arXiv2011.07407MaRDI QIDQ6353752FDOQ6353752
Isak Falk, Kate Highnam, Daniel Lengyel, Marc Peter Deisenroth, Janith Petangoda, Michalis Lazarou, Nicholas R. Jennings, Arinbjorn Kolbeinsson
Publication date: 14 November 2020
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.
Has companion code repository: https://github.com/Do-Not-Circulate/GENNI
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)
