Adam revisited: a weighted past gradients perspective
- 3 January 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Frontiers of Computer Science
- Vol. 14 (5), 1-16
- https://doi.org/10.1007/s11704-019-8457-x
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Nostalgic Adam: Weighting More of the Past Gradients When Designing the Adaptive Learning RatePublished by International Joint Conferences on Artificial Intelligence ,2019
- Transcribing Content from Structural Images with Spotlight MechanismPublished by Association for Computing Machinery (ACM) ,2018
- Finding Similar Exercises in Online Education SystemsPublished by Association for Computing Machinery (ACM) ,2018
- Dopamine crosslinked graphene oxide membrane for simultaneous removal of organic pollutants and trace heavy metals from aqueous solutionEnvironmental Technology, 2017
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Introduction to Online Convex OptimizationFoundations and Trends® in Optimization, 2015
- On the Generalization Ability of On-Line Learning AlgorithmsIEEE Transactions on Information Theory, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Term-weighting approaches in automatic text retrievalInformation Processing & Management, 1988
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951