Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.16425 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916626080727040 |
|---|---|
| author | Mhaskar, Hrushikesh O'Dowd, Ryan Tsoukanis, Efstratios |
| author_facet | Mhaskar, Hrushikesh O'Dowd, Ryan Tsoukanis, Efstratios |
| contents | In machine learning, classification is usually seen as a function approximation problem, where the goal is to learn a function that maps input features to class labels. In this paper, we propose a novel clustering and classification framework inspired by the principles of signal separation. This approach enables efficient identification of class supports, even in the presence of overlapping distributions. We validate our method on real-world hyperspectral datasets Salinas and Indian Pines. The experimental results demonstrate that our method is competitive with the state of the art active learning algorithms by using a very small subset of data set as training points. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16425 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Learning Classification from a Signal Separation Perspective Mhaskar, Hrushikesh O'Dowd, Ryan Tsoukanis, Efstratios Machine Learning Optimization and Control In machine learning, classification is usually seen as a function approximation problem, where the goal is to learn a function that maps input features to class labels. In this paper, we propose a novel clustering and classification framework inspired by the principles of signal separation. This approach enables efficient identification of class supports, even in the presence of overlapping distributions. We validate our method on real-world hyperspectral datasets Salinas and Indian Pines. The experimental results demonstrate that our method is competitive with the state of the art active learning algorithms by using a very small subset of data set as training points. |
| title | Active Learning Classification from a Signal Separation Perspective |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2502.16425 |