عرض بسيط للتسجيلة

المؤلفGanaie, M. A.
المؤلفHu, Minghui
المؤلفMalik, A. K.
المؤلفTanveer, M.
المؤلفSuganthan, P. N.
تاريخ الإتاحة2023-02-12T10:02:05Z
تاريخ النشر2022-10-01
اسم المنشورEngineering Applications of Artificial Intelligence
المعرّفhttp://dx.doi.org/10.1016/j.engappai.2022.105151
الاقتباسGanaie, M. A., Hu, M., Malik, A. K., Tanveer, M., & Suganthan, P. N. (2022). Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115, 105151.‏
الرقم المعياري الدولي للكتاب09521976
معرّف المصادر الموحدhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85135374954&origin=inward
معرّف المصادر الموحدhttp://hdl.handle.net/10576/39985
الملخصEnsemble learning combines several individual models to obtain better generalization performance. Currently, deep learning architectures are showing better performance compared to the shallow or traditional models. Deep ensemble learning models combine the advantages of both the deep learning models as well as the ensemble learning such that the final model has better generalization performance. This paper reviews the state-of-art deep ensemble models and hence serves as an extensive summary for the researchers. The ensemble models are broadly categorized into bagging, boosting, stacking, negative correlation based deep ensemble models, explicit/implicit ensembles, homogeneous/heterogeneous ensemble, decision fusion strategies based deep ensemble models. Applications of deep ensemble models in different domains are also briefly discussed. Finally, we conclude this paper with some potential future research directions.
راعي المشروعthis work is provided by the National Supercomputing Mission under DST and Miety, Govt. of India under Grant No. DST/NSM/ R&D_HPC_Appl/2021/03.29 , as well as the D Department of Science and Technology under Interdisciplinary Cyber Physical Systems (ICPS) Scheme grant no. DST/ICPS/CPS-Individual/2018/276 . Mr. Ashwani Kumar Malik acknowledges the financial support (File no - 09/1022 (0075)/2019-EMR-I ) given as scholarship by Council of Scientific and Industrial Research (CSIR), New Delhi, India . We are grateful to IIT Indore for the facilities and support being provided.
اللغةen
الناشرElsevier Ltd
الموضوعDeep learning
Ensemble learning
العنوانEnsemble deep learning: A review
النوعOther
رقم المجلد115
dc.accessType Open Access


الملفات في هذه التسجيلة

Thumbnail

هذه التسجيلة تظهر في المجموعات التالية

عرض بسيط للتسجيلة