Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.14383 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909208362876928 |
|---|---|
| author | Hong, Yifan Wang, Chen |
| author_facet | Hong, Yifan Wang, Chen |
| contents | Humans can categorize with only a few samples despite the numerous features. To mimic this ability, we propose a novel dimension-reduced category representation using a mixture of probabilistic principal component analyzers (mPPCA). Tests on the ${\tt CIFAR-10H}$ dataset demonstrate that mPPCA with only a single principal component for each category effectively predicts human categorization of natural images. We further impose a hierarchical prior on mPPCA to account for new category generalization. mPPCA captures human behavior in our experiments on images with simple size-color combinations. We also provide sufficient and necessary conditions when reducing dimensions in categorization is rational. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_14383 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Rational Model of Dimension-reduced Human Categorization Hong, Yifan Wang, Chen Machine Learning Artificial Intelligence Humans can categorize with only a few samples despite the numerous features. To mimic this ability, we propose a novel dimension-reduced category representation using a mixture of probabilistic principal component analyzers (mPPCA). Tests on the ${\tt CIFAR-10H}$ dataset demonstrate that mPPCA with only a single principal component for each category effectively predicts human categorization of natural images. We further impose a hierarchical prior on mPPCA to account for new category generalization. mPPCA captures human behavior in our experiments on images with simple size-color combinations. We also provide sufficient and necessary conditions when reducing dimensions in categorization is rational. |
| title | A Rational Model of Dimension-reduced Human Categorization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2305.14383 |