Name
Title | ||
|---|---|---|
Stepwise Pathnet: Transfer Learning Algorithm To Improve Network Structure Versatility |
Abstract | ||
|---|---|---|
Transfer learning can train a neural network for a target task's small dataset using a source task's pre-trained network; however, catastrophic forgetting, where the knowledge of the pre-trained network disappears during transfer learning, is problematic in this setting. PathNet was proposed to address this problem. However, PathNet can only be applied to modular neural network cases:thus, a non-modular pre-trained neural network is unavailable. Consequently, PathNet cannot be used to improve network structure versatility. Therefore, we propose Stepwise PathNet to improve versatility by considering the layers of a non-modular pre-trained neural network as modules. The performances of the proposed Stepwise and original PathNet methods were compared using the CIFAR-10 dataset (10 classes, and 60,000 images), and the results confirm the proposed method's potential to stabilize learning curves and accelerate learning to 45%. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/SMC.2018.00163 | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) |
Field | DocType | ISSN |
Forgetting,Computer science,Transfer of learning,Modular neural network,Artificial intelligence,Learning curve,Artificial neural network,Machine learning,Network structure | Conference | 1062-922X |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shunsuke Imai | 1 | 0 | 0.34 |
| Hajime Nobuhara | 2 | 192 | 34.02 |