| Autor: |
Md Tauhidul Islam, Zixia Zhou, Hongyi Ren, Masoud Badiei Khuzani, Daniel Kapp, James Zou, Lu Tian, Joseph C. Liao, Lei Xing |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Nature Communications, Vol 14, Iss 1, Pp 1-20 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2041-1723 |
| DOI: |
10.1038/s41467-023-43958-w |
| Popis: |
Abstract Deep neural networks (DNNs) extract thousands to millions of task-specific features during model training for inference and decision-making. While visualizing these features is critical for comprehending the learning process and improving the performance of the DNNs, existing visualization techniques work only for classification tasks. For regressions, the feature points lie on a high dimensional continuum having an inherently complex shape, making a meaningful visualization of the features intractable. Given that the majority of deep learning applications are regression-oriented, developing a conceptual framework and computational method to reliably visualize the regression features is of great significance. Here, we introduce a manifold discovery and analysis (MDA) method for DNN feature visualization, which involves learning the manifold topology associated with the output and target labels of a DNN. MDA leverages the acquired topological information to preserve the local geometry of the feature space manifold and provides insightful visualizations of the DNN features, highlighting the appropriateness, generalizability, and adversarial robustness of a DNN. The performance and advantages of the MDA approach compared to the existing methods are demonstrated in different deep learning applications. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full text from SpringerLink