Digital transformation of thermal and cold spray processes with emphasis on machine learning

K Malamousi, K Delibasis, B Allcock… - Surface and Coatings …, 2022 - Elsevier
Thermal spray technologies continuously evolve to meet new challenges arising from
current and future market needs and requirements. This evolution has been well …

Privacy preserving Federated Learning framework for IoMT based big data analysis using edge computing

AK Nair, J Sahoo, ED Raj - Computer Standards & Interfaces, 2023 - Elsevier
The current industrial scenario has witnessed the application of several artificial intelligence-
based technologies for mining and processing IoMT-based big data. An emerging …

Adam can converge without any modification on update rules

Y Zhang, C Chen, N Shi, R Sun… - Advances in neural …, 2022 - proceedings.neurips.cc
Ever since\citet {reddi2019convergence} pointed out the divergence issue of Adam, many
new variants have been designed to obtain convergence. However, vanilla Adam remains …

A simple convergence proof of adam and adagrad

A Défossez, L Bottou, F Bach, N Usunier - arXiv preprint arXiv:2003.02395, 2020 - arxiv.org
We provide a simple proof of convergence covering both the Adam and Adagrad adaptive
optimization algorithms when applied to smooth (possibly non-convex) objective functions …

A wavelet-based deep learning pipeline for efficient COVID-19 diagnosis via CT slices

O Attallah, A Samir - Applied Soft Computing, 2022 - Elsevier
The quick diagnosis of the novel coronavirus (COVID-19) disease is vital to prevent its
propagation and improve therapeutic outcomes. Computed tomography (CT) is believed to …

Provable adaptivity of adam under non-uniform smoothness

B Wang, Y Zhang, H Zhang, Q Meng, R Sun… - Proceedings of the 30th …, 2024 - dl.acm.org
Adam is widely adopted in practical applications due to its fast convergence. However, its
theoretical analysis is still far from satisfactory. Existing convergence analyses for Adam rely …

Closing the gap between the upper bound and lower bound of Adam's iteration complexity

B Wang, J Fu, H Zhang, N Zheng… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Recently, Arjevani et al.[1] establish a lower bound of iteration complexity for the
first-order optimization under an $ L $-smooth condition and a bounded noise variance …

Momentum provably improves error feedback!

I Fatkhullin, A Tyurin, P Richtárik - Advances in Neural …, 2024 - proceedings.neurips.cc
Due to the high communication overhead when training machine learning models in a
distributed environment, modern algorithms invariably rely on lossy communication …

[HTML][HTML] Advanced Deep Learning Techniques for Battery Thermal Management in New Energy Vehicles

S Qi, Y Cheng, Z Li, J Wang, H Li, C Zhang - Energies, 2024 - mdpi.com
In the current era of energy conservation and emission reduction, the development of
electric and other new energy vehicles is booming. With their various attributes, lithium …

DecentLaM: Decentralized momentum SGD for large-batch deep training

K Yuan, Y Chen, X Huang, Y Zhang… - Proceedings of the …, 2021 - openaccess.thecvf.com
The scale of deep learning nowadays calls for efficient distributed training algorithms.
Decentralized momentum SGD (DmSGD), in which each node averages only with its …