Searching for internal symbols underlying deep learning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910701902102528 |
|---|---|
| author | Lee, Jung H. Vijayan, Sujith |
| author_facet | Lee, Jung H. Vijayan, Sujith |
| contents | Deep learning (DL) enables deep neural networks (DNNs) to automatically learn complex tasks or rules from given examples without instructions or guiding principles. As we do not engineer DNNs' functions, it is extremely difficult to diagnose their decisions, and multiple lines of studies proposed to explain the principles of their operations. Notably, one line of studies suggests that DNNs may learn concepts, the high level features that are recognizable to humans. In this study, we extend this line of studies and hypothesize that DNNs can develop abstract codes that can be used to augment DNNs' decision-making. To address this hypothesis, we combine foundation segmentation models and unsupervised learning to extract internal codes and identify potential use of abstract codes to make DL's decision-making more reliable and safer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Searching for internal symbols underlying deep learning Lee, Jung H. Vijayan, Sujith Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Deep learning (DL) enables deep neural networks (DNNs) to automatically learn complex tasks or rules from given examples without instructions or guiding principles. As we do not engineer DNNs' functions, it is extremely difficult to diagnose their decisions, and multiple lines of studies proposed to explain the principles of their operations. Notably, one line of studies suggests that DNNs may learn concepts, the high level features that are recognizable to humans. In this study, we extend this line of studies and hypothesize that DNNs can develop abstract codes that can be used to augment DNNs' decision-making. To address this hypothesis, we combine foundation segmentation models and unsupervised learning to extract internal codes and identify potential use of abstract codes to make DL's decision-making more reliable and safer. |
| title | Searching for internal symbols underlying deep learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.20605 |