Show simple item record

AuthorHu, Minghui
AuthorGao, Ruobin
AuthorSuganthan, Ponnuthurai N.
AuthorTanveer, M.
Available date2023-02-08T10:53:35Z
Publication Date2022-12-01
Publication NameNeurocomputing
Identifierhttp://dx.doi.org/10.1016/j.neucom.2022.09.148
CitationHu, M., Gao, R., Suganthan, P. N., & Tanveer, M. (2022). Automated layer-wise solution for ensemble deep randomized feed-forward neural network. Neurocomputing, 514, 137-147.‏
ISSN09252312
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85139367537&origin=inward
URIhttp://hdl.handle.net/10576/39840
AbstractThe randomized feed-forward neural network is a single hidden layer feed-forward neural network that enables efficient learning by optimizing only the output weights. The ensemble deep learning framework significantly improves the performance of randomized neural networks. However, the framework's capabilities are limited by traditional hyper-parameter selection approaches. Meanwhile, different random network architectures, such as the existence or lack of a direct link and the mapping of direct links, can also strongly affect the results. We present an automated learning pipeline for the ensemble deep randomized feed-forward neural network in this paper, which integrates hyper-parameter selection and randomized network architectural search via Bayesian optimization to ensure robust performance. Experiments on 46 UCI tabular datasets show that our strategy produces state-of-the-art performance on various tabular datasets among a range of randomized networks and feed-forward neural networks. We also conduct ablation studies to investigate the impact of various hyper-parameters and network architectures.
Languageen
PublisherElsevier B.V.
SubjectAutomated machine learning
Bayesian optimization
Ensemble deep random vector functional link
Random vector functional link
Randomized feed-forward neural network
TitleAutomated layer-wise solution for ensemble deep randomized feed-forward neural network
TypeArticle
Pagination137-147
Volume Number514
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record