Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio

Autor: König, H.M.T., Hoos, H.H., Rijn, J.N. van

Publikováno v: Machine Learning, 111, 4565-4584
Machine learning 111(12), 4565-4584 (2022). doi:10.1007/s10994-022-06212-w

Machine learning 111(12), 4565-4584 (2022). doi:10.1007/s10994-022-06212-w
Published by Springer Science + Business Media B.V, Dordrecht [u.a.]

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3393b15c9ca84040a19624fd42acceb0
http://hdl.handle.net/1887/3484755

Hyper-parameter optimization for latent spaces

Autor: Veloso, B., Carprese, L., König, H.M.T., Manco, G., Hoos, H.H., Gama, J., Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A., Teixeira S.

Publikováno v: Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021, 249-264. Cham: Springer International Publishing
STARTPAGE=249;ENDPAGE=264;TITLE=Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021

We present an online optimization method for time-evolving data streams that can automatically adapt the hyper-parameters of an embedding model. More specifically, we employ the Nelder-Mead algorithm, which uses a set of heuristics to produce and exp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::59a5859916a15467778ac3acd584745d
https://hdl.handle.net/1887/3277022