التفاصيل البيبلوغرافية
| العنوان: |
CMNN: Coupled Modular Neural Network |
| المؤلفون: |
Md Intisar Chowdhury, Qiangfu Zhao, Kai Su, Yong Liu |
| المصدر: |
IEEE Access, Vol 9, Pp 93871-93891 (2021) |
| بيانات النشر: |
IEEE, 2021. |
| سنة النشر: |
2021 |
| المجموعة: |
LCC:Electrical engineering. Electronics. Nuclear engineering |
| مصطلحات موضوعية: |
Artificial intelligence, modular neural networks, deep learning, ensemble learning, knowledge-distillation, multi-class classification, Electrical engineering. Electronics. Nuclear engineering, TK1-9971 |
| الوصف: |
In this paper, we propose a multi-branch neural network architecture named Coupled Modular Neural Network (CMNN). A CMNN is a network consisting of $\beta $ closely coupled sub-networks, where $\beta $ is termed as the branching factor in this paper. We call the whole network a super-graph and each sub-network a sub-graph. Each sub-graph is a stand-alone neural network and shares a common block with other sub-graphs. To effectively leverage the super-graph we propose a simple but easy-to-implement Round-Robin-based learning algorithm. Each training iteration contains two phases. In the first phase, we choose a sub-graph in a Round-Robin fashion and train it using knowledge of the super-graph (distillation). In the second phase, we fine-tune the super-graph based on the updated sub-graphs. This algorithm produces a different copy of the super-graph at each iteration which acts as an improved teacher network for the sub-graph; and a different copy of one of the sub-graphs which functions as a new building block for the super-graph. To validate and test CMNN and the proposed algorithm, we conduct experiments on CIFAR-10, CIFAR-100, Tiny ImageNet and a private On-Road-Risk (ORR) datasets. Empirical results on all these four datasets indicate that we not only obtain a strong sub-graph network, the learning framework can also produce strong ensemble performance which substantiates the diversity introduced throughout the learning framework. |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2169-3536 |
| Relation: |
https://ieeexplore.ieee.org/document/9468686/; https://doaj.org/toc/2169-3536 |
| DOI: |
10.1109/ACCESS.2021.3093541 |
| URL الوصول: |
https://doaj.org/article/060ea740c0ad43e8825a66ac656b00c9 |
| رقم الانضمام: |
edsdoj.060ea740c0ad43e8825a66ac656b00c9 |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder