Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.17651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916226615214080 |
|---|---|
| author | Keskinen, Santtu |
| author_facet | Keskinen, Santtu |
| contents | In class incremental learning, neural networks typically suffer from catastrophic forgetting. We show that an MLP featuring a sparse activation function and an adaptive learning rate optimizer can compete with established regularization techniques in the Split-MNIST task. We highlight the effectiveness of the Adaptive SwisH (ASH) activation function in this context and introduce a novel variant, Hard Adaptive SwisH (Hard ASH) to further enhance the learning retention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17651 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hard ASH: Sparsity and the right optimizer make a continual learner Keskinen, Santtu Machine Learning Computer Vision and Pattern Recognition In class incremental learning, neural networks typically suffer from catastrophic forgetting. We show that an MLP featuring a sparse activation function and an adaptive learning rate optimizer can compete with established regularization techniques in the Split-MNIST task. We highlight the effectiveness of the Adaptive SwisH (ASH) activation function in this context and introduce a novel variant, Hard Adaptive SwisH (Hard ASH) to further enhance the learning retention. |
| title | Hard ASH: Sparsity and the right optimizer make a continual learner |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17651 |