Salvato in:
Dettagli Bibliografici
Autori principali: Oubaha, Brahim, Berrou, Claude, Ji, Xueyao, Nasser, Yehya, Bidan, Raphaël Le
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.12599
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916328430895104
author Oubaha, Brahim
Berrou, Claude
Ji, Xueyao
Nasser, Yehya
Bidan, Raphaël Le
author_facet Oubaha, Brahim
Berrou, Claude
Ji, Xueyao
Nasser, Yehya
Bidan, Raphaël Le
contents Diversity is a concept of prime importance in almost all disciplines based on information processing. In telecommunications, for example, spatial, temporal, and frequency diversity, as well as redundant coding, are fundamental concepts that have enabled the design of extremely efficient systems. In machine learning, in particular with neural networks, diversity is not always a concept that is emphasized or at least clearly identified. This paper proposes a neural network architecture that builds upon various diversity principles, some of them already known, others more original. Our architecture obtains remarkable results, with a record self-supervised learning accuracy of 99. 57% in MNIST, and a top tier promising semi-supervised learning accuracy of 94.21% in CIFAR-10 using only 25 labels per class.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12599
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Diversity in Discriminative Neural Networks
Oubaha, Brahim
Berrou, Claude
Ji, Xueyao
Nasser, Yehya
Bidan, Raphaël Le
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Diversity is a concept of prime importance in almost all disciplines based on information processing. In telecommunications, for example, spatial, temporal, and frequency diversity, as well as redundant coding, are fundamental concepts that have enabled the design of extremely efficient systems. In machine learning, in particular with neural networks, diversity is not always a concept that is emphasized or at least clearly identified. This paper proposes a neural network architecture that builds upon various diversity principles, some of them already known, others more original. Our architecture obtains remarkable results, with a record self-supervised learning accuracy of 99. 57% in MNIST, and a top tier promising semi-supervised learning accuracy of 94.21% in CIFAR-10 using only 25 labels per class.
title On Diversity in Discriminative Neural Networks
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.12599