Improving SeNA-CNN by Automating Task Recognition
Catastrophic forgetting arises when a neural network is not capable of preserving the past learned task when learning a new task. There are already some methods proposed to mitigate this problem in arti cial neural networks. In this paper we propose to improve upon our previous state-of-the-art meth...
| Autor principal: | |
|---|---|
| Outros Autores: | |
| Formato: | conferenceObject |
| Idioma: | eng |
| Publicado em: |
2020
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10400.6/8145 |
| País: | Portugal |
| Oai: | oai:ubibliorum.ubi.pt:10400.6/8145 |