Dropout, a basic and effective regularization method for a deep learning model: a case study
Deep learning is based on a network of artificial neurons inspired by the human brain. This network is made up of tens or even hundreds of "layers" of neurons. The fields of application of deep learning are indeed multiple; Agriculture is one of those fields in which deep learning is used...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | EJournal Article |
| Published: |
Institute of Advanced Engineering and Science,
2021-11-01.
|
| Subjects: | |
| Online Access: | Get fulltext |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| LEADER | 02377 am a22003013u 4500 | ||
|---|---|---|---|
| 001 | ijeecs24273_15721 | ||
| 042 | |a dc | ||
| 100 | 1 | 0 | |a Jabir, Brahim |e author |
| 100 | 1 | 0 | |e contributor |
| 700 | 1 | 0 | |a Falih, Noureddine |e author |
| 245 | 0 | 0 | |a Dropout, a basic and effective regularization method for a deep learning model: a case study |
| 260 | |b Institute of Advanced Engineering and Science, |c 2021-11-01. | ||
| 500 | |a https://ijeecs.iaescore.com/index.php/IJEECS/article/view/24273 | ||
| 520 | |a Deep learning is based on a network of artificial neurons inspired by the human brain. This network is made up of tens or even hundreds of "layers" of neurons. The fields of application of deep learning are indeed multiple; Agriculture is one of those fields in which deep learning is used in various agricultural problems (disease detection, pest detection, and weed identification). A major problem with deep learning is how to create a model that works well, not only on the learning set but also on the validation set. Many approaches used in neural networks are explicitly designed to reduce overfit, possibly at the expense of increasing validation accuracy and training accuracy. In this paper, a basic technique (dropout) is proposed to minimize overfit, we integrated it into a convolutional neural network model to classify weed species and see how it impacts performance, a complementary solution (exponential linear units) are proposed to optimize the obtained results. The results showed that these proposed solutions are practical and highly accurate, enabling us to adopt them in deep learning models. | ||
| 540 | |a Copyright (c) 2021 Institute of Advanced Engineering and Science | ||
| 540 | |a http://creativecommons.org/licenses/by-nc/4.0 | ||
| 546 | |a eng | ||
| 690 | |||
| 690 | |a CNN; Deep learning; Dropout; Machine learning; Regularization; | ||
| 655 | 7 | |a info:eu-repo/semantics/article |2 local | |
| 655 | 7 | |a info:eu-repo/semantics/publishedVersion |2 local | |
| 655 | 7 | |2 local | |
| 786 | 0 | |n Indonesian Journal of Electrical Engineering and Computer Science; Vol 24, No 2: November 2021; 1009-1016 | |
| 786 | 0 | |n 2502-4760 | |
| 786 | 0 | |n 2502-4752 | |
| 786 | 0 | |n 10.11591/ijeecs.v24.i2 | |
| 787 | 0 | |n https://ijeecs.iaescore.com/index.php/IJEECS/article/view/24273/15721 | |
| 856 | 4 | 1 | |u https://ijeecs.iaescore.com/index.php/IJEECS/article/view/24273/15721 |z Get fulltext |