Stochastic gradient descent for nonconvex learning without bounded gradient assumptions
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 …
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
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 …
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
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 …
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
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 …
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 …
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
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 …
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
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 …
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
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 …
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
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 …
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 …
plus education and online learning platforms. Learning efficacy is the leading impactor of …