Deep learning regularization techniques to genomics data
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 L1 and L2 a...
Main Authors: | Harouna Soumare, Alia Benkahla, Nabil Gmati |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-09-01
|
Series: | Array |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005621000163 |
Similar Items
-
Regularization Effects in Deep Learning Architecture
by: Muhammad Dahiru Liman, et al.
Published: (2024-03-01) -
A Review on Dropout Regularization Approaches for Deep Neural Networks within the Scholarly Domain
by: Imrus Salehin, et al.
Published: (2023-07-01) -
Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network
by: Ivana Marin, et al.
Published: (2020-11-01) -
Double Consistency Regularization for Transformer Networks
by: Yuxian Wan, et al.
Published: (2023-10-01) -
Sequence-Dropout Block for Reducing Overfitting Problem in Image Classification
by: Ledan Qian, et al.
Published: (2020-01-01)