Title | ||
---|---|---|
Stabilization of the Modular Selective Neural Network Model Based on Inter-Class Correlation |
Abstract | ||
---|---|---|
We propose an optimization of Modular Selective Network or MS-Net by reducing the number of expert network evaluations. MS-Net is composed of a router and a set of expert networks. In our original proposal, MS-Net is constructed based on a Round-Robin dataset partition with controlled redundancy among the subsets of classes. In this paper, we propose a novel way for reducing the inference cost by ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CYBCONF51991.2021.9464136 | 2021 5th IEEE International Conference on Cybernetics (CYBCONF) |
Keywords | DocType | ISBN |
Correlation,Conferences,Redundancy,Neural networks,Fault tolerant systems,Focusing,Neck | Conference | 978-1-6654-0320-7 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chowdhury Md INTISAR | 1 | 0 | 0.34 |
KAI SU | 2 | 0 | 0.34 |
HUITAO WANG | 3 | 0 | 0.34 |
Qiangfu Zhao | 4 | 214 | 62.36 |