Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Okerinde, Ademola"'
Autor:
Okerinde, Ademola, Hoggatt, Sam, Lakkireddy, Divya Vani, Brubaker, Nolan, Hsu, William, Shamir, Lior, Spiesman, Brian
Publikováno v:
The 4th International Conference on Computing and Data Science (CONF-CDS 2022)
In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is the measur
Externí odkaz:
http://arxiv.org/abs/2201.01391
Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to trained models that are unusable for any practical purpose. In this study we explore an unsupervised approach to address these imbalances by lev
Externí odkaz:
http://arxiv.org/abs/2104.04162
Ceramic insulators are important to electronic systems, designed and installed to protect humans from the danger of high voltage electric current. However, insulators are not immortal, and natural deterioration can gradually damage them. Therefore, t
Externí odkaz:
http://arxiv.org/abs/2103.01426
Autor:
Okerinde, Ademola, Hoggatt, Sam, Lakkireddy, Divya Vani, Brubaker, Nolan, Hsu, William, Shamir, Lior, Spiesman, Brian
Publikováno v:
Journal of Physics: Conference Series; Jul2023, Vol. 2547 Issue 1, p1-9, 9p
