Deep Learning and Geometric Deep Learning: An introduction for mathematicians and physicists
R Fioresi, F Zanchetta - … Journal of Geometric Methods in Modern …, 2023 - World Scientific
In this expository paper, we want to give a brief introduction, with few key references for
further reading, to the inner functioning of the new and successful algorithms of Deep …
further reading, to the inner functioning of the new and successful algorithms of Deep …
Toward large kernel models
Recent studies indicate that kernel machines can often perform similarly or better than deep
neural networks (DNNs) on small datasets. The interest in kernel machines has been …
neural networks (DNNs) on small datasets. The interest in kernel machines has been …
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
In this paper, we first present an explanation regarding the common occurrence of spikes in
the training loss when neural networks are trained with stochastic gradient descent (SGD) …
the training loss when neural networks are trained with stochastic gradient descent (SGD) …
On emergence of clean-priority learning in early stopped neural networks
When random label noise is added to a training dataset, the prediction error of a neural
network on a label-noise-free test dataset initially improves during early training but …
network on a label-noise-free test dataset initially improves during early training but …
Toward Understanding the Dynamics of Over-parameterized Neural Networks
L Zhu - 2024 - search.proquest.com
The practical applications of neural networks are vast and varied, yet a comprehensive
understanding of their underlying principles remains incomplete. This dissertation advances …
understanding of their underlying principles remains incomplete. This dissertation advances …
Mechanism of clean-priority learning in early stopped neural networks of infinite width
When random label noise is added to a training dataset, the prediction error of a neural
network on a label-noise-free test dataset initially improves during early training but …
network on a label-noise-free test dataset initially improves during early training but …