A comprehensive survey on regularization strategies in machine learning
Y Tian, Y Zhang - Information Fusion, 2022 - Elsevier
In machine learning, the model is not as complicated as possible. Good generalization
ability means that the model not only performs well on the training data set, but also can …
ability means that the model not only performs well on the training data set, but also can …
The mathematical foundations of manifold learning
L Melas-Kyriazi - arXiv preprint arXiv:2011.01307, 2020 - arxiv.org
Manifold learning is a popular and quickly-growing subfield of machine learning based on
the assumption that one's observed data lie on a low-dimensional manifold embedded in a …
the assumption that one's observed data lie on a low-dimensional manifold embedded in a …
Geometric regularization of local activations for knowledge transfer in Convolutional Neural Networks
In this work, we propose a mechanism for knowledge transfer between Convolutional Neural
Networks via the geometric regularization of local features produced by the activations of …
Networks via the geometric regularization of local features produced by the activations of …
Rail transit OD‐matrix completion via manifold regularized tensor factorisation
Urban rail transit has become an indispensable mode in major cities worldwide regarding
the advantages of large capacity, high speed, punctuality, and environmental protection …
the advantages of large capacity, high speed, punctuality, and environmental protection …
[PDF][PDF] The geometry of semi-supervised learning
L Melas-Kyriazi - PhD thesis, 2020 - math.harvard.edu
From an early age, our parents and teachers impress upon us the importance of learning.
We go to school, do homework, and write senior theses in the name of learning. But what …
We go to school, do homework, and write senior theses in the name of learning. But what …