Enhancing network modularity to mitigate catastrophic forgetting
Abstract Catastrophic forgetting occurs when learning algorithms change connections used to encode previously acquired skills to learn a new skill. Recently, a modular approach for neural networks was deemed necessary as learning problems grow in scale and complexity since it intuitively should redu...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-11-01
|
| Series: | Applied Network Science |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41109-020-00332-9 |