Carta Acesso aberto Revisado por pares

Reply to Huszár: The elastic weight consolidation penalty is empirically valid

2018; National Academy of Sciences; Volume: 115; Issue: 11 Linguagem: Inglês

10.1073/pnas.1800157115

ISSN

1091-6490

Autores

James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska‐Barwińska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell,

Tópico(s)

Machine Learning in Materials Science

Resumo

In our recent work on elastic weight consolidation (EWC) (1) we show that forgetting in neural networks can be alleviated by using a quadratic penalty whose derivation was inspired by Bayesian evidence accumulation. In his letter (2), Dr. Huszar provides an alternative form for this penalty by following the standard work on expectation propagation using the Laplace approximation (3). He correctly argues that in cases when more than two tasks are undertaken the two forms of the penalty are different. Dr. Huszar also shows that for a toy linear regression problem his expression appears to be better. We would like to thank Dr. Huszar for pointing out … [↵][1]1To whom correspondence should be addressed. Email: kirkpatrick@google.com. [1]: #xref-corresp-1-1

Referência(s)