Deep learning regularization techniques to genomics data - Archive ouverte HAL Access content directly
Journal Articles Array Year : 2021

Deep learning regularization techniques to genomics data

(1, 2) , (2) , (3)
1
2
3

Abstract

Deep Learning algorithms have achieved a great success in many domains where large scale datasets are used. However, training these algorithms on high dimensional data requires the adjustment of many parameters. Avoiding overfitting problem is difficult. Regularization techniques such as L 1 and L 2 are used to prevent the parameters of training model from being large. Another commonly used regularization method called Dropout randomly removes some hidden units during the training phase. In this work, we describe some architectures of Deep Learning algorithms, we explain optimization process for training them and attempt to establish a theoretical relationship between L 2-regularization and Dropout. We experimentally compare the effect of these techniques on the learning model using genomics datasets.
Fichier principal
Vignette du fichier
1212.pdf (657.29 Ko) Télécharger le fichier
Origin : Publication funded by an institution

Dates and versions

pasteur-03548830 , version 1 (31-01-2022)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Harouna Soumare, Alia Benkahla, Nabil Gmati. Deep learning regularization techniques to genomics data. Array, 2021, 11, pp.100068. ⟨10.1016/j.array.2021.100068⟩. ⟨pasteur-03548830⟩

Collections

RIIP RIIP_TUNIS
13 View
12 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More