Leverage estimation for multi-output neural networks
Tomasz Grel , Stanisław Jankowski
AbstractThe article deals with the problem of computing the leverages for multi-output neural networks. The leverages can be subsequently used for determining which learning examples have the strongest inﬂuence on the model. Therefore computing them may provide researchers with important insights about the constructed model. More speciﬁcally they can be used to detect overﬁtting. A step by step algorithm for computing the Jacobian matrix and the leverages is presented, along with an example application to a synthetic problem.
|Publication size in sheets||0.5|
|Book||Romaniuk Ryszard (eds.): Proc. SPIE. 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, vol. 10031, 2016, P.O. Box 10, Bellingham, Washington 98227-0010 USA , SPIE , ISBN 9781510604858, [781510604865 (electronic) ], 1170 p., DOI:10.1117/12.2257157|
|Keywords in English||Dimensionality reduction, inﬂuence statistics, leverages, hat matrix, artiﬁcial neural networks, Nonlinear PCA, overﬁtting|
|Score|| = 15.0, 10-01-2020, BookChapterMatConfByConferenceseries|
= 15.0, 10-01-2020, BookChapterMatConfByConferenceseries
|Publication indicators||= 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.