Stochastic gradient descent for nonconvex learning without bounded gradient assumptions

Y Lei, T Hu, G Li, K Tang - IEEE transactions on neural …, 2019 - ieeexplore.ieee.org
Stochastic gradient descent (SGD) is a popular and efficient method with wide applications
in training deep neural nets and other nonconvex models. While the behavior of SGD is well …

A multivariate adaptive gradient algorithm with reduced tuning efforts

S Saab Jr, K Saab, S Phoha, M Zhu, A Ray - Neural Networks, 2022 - Elsevier
Large neural networks usually perform well for executing machine learning tasks. However,
models that achieve state-of-the-art performance involve arbitrarily large number of …

A short-term energy prediction system based on edge computing for smart city

H Luo, H Cai, H Yu, Y Sun, Z Bi, L Jiang - Future Generation Computer …, 2019 - Elsevier
The development of Internet of Things technologies has provided potential for real-time
monitoring and control of environment in smart cities. In the field of energy management …

Generalization performance of multi-pass stochastic gradient descent with convex loss functions

Y Lei, T Hu, K Tang - Journal of Machine Learning Research, 2021 - jmlr.org
Stochastic gradient descent (SGD) has become the method of choice to tackle large-scale
datasets due to its low computational cost and good practical performance. Learning rate …

Robust echo state network with sparse online learning

C Yang, K Nie, J Qiao, D Wang - Information Sciences, 2022 - Elsevier
Echo state network (ESN) is an effective tool for nonlinear systems modeling. To handle
irregular noises or outliers in practical systems and alleviate the overfitting issue, the robust …

Data-based modelling of proton exchange membrane fuel cell performance and degradation dynamics

A Legala, S Shahgaldi, X Li - Energy Conversion and Management, 2023 - Elsevier
Proton exchange membrane fuel cell (PEMFC) is in the commercial adoption process for
hard-to-decarbonize applications such as transport. However, its long-term durability …

Feedback loops in machine learning: A study on the interplay of continuous updating and human discrimination

K Bauer, R Heigl, O Hinz, M Kosfeld - Journal of the Association for …, 2024 - aisel.aisnet.org
Abstract Machine learning (ML) models often endogenously shape the data available for
future updates. This is important because of their role in influencing human decisions, which …

Early expression detection via online multi-instance learning with nonlinear extension

L **e, D Tao, H Wei - IEEE Transactions on Neural Networks …, 2018 - ieeexplore.ieee.org
Video-based facial expression recognition has received substantial attention over the past
decade, while early expression detection (EED) is still a relatively new and challenging …

BNGBS: an efficient network boosting system with triple incremental learning capabilities for more nodes, samples, and classes

L Feng, C Zhao, CLP Chen, YL Li, M Zhou, H Qiao… - Neurocomputing, 2020 - Elsevier
As an ensemble algorithm, network boosting enjoys a powerful classification ability but
suffers from the tedious and time-consuming training process. To tackle the problem, in this …

Influence of self-efficacy improvement on online learning participation

L Geng - International Journal of Emerging Technologies in …, 2022 - learntechlib.org
More and more online learning apps are emerging, thanks to the development of Internet
plus education and online learning platforms. Learning efficacy is the leading impactor of …