Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2405.15135 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911203081584640 |
|---|---|
| author | Yang, Xianglin Dong, Jin Song |
| author_facet | Yang, Xianglin Dong, Jin Song |
| contents | Monitoring the inner state of deep neural networks is essential for auditing the learning process and enabling timely interventions. While conventional metrics like validation loss offer a surface-level view of performance, the evolution of a model's hidden representations provides a deeper, complementary window into its internal dynamics. However, the literature lacks a real-time tool to monitor these crucial internal states. To address this, we introduce SentryCam, a live-update visualization framework that tracks the progression of hidden representations throughout training. SentryCam produces high-fidelity visualizations of the evolving representation space with minimal latency, serving as a powerful dashboard for understanding how a model learns. We quantitatively validate the faithfulness of SentryCam's visualizations across diverse datasets and architectures (ResNet, ViT). Furthermore, we demonstrate SentryCam's practical utility for model auditing through a case study on training instability. We designed an automated auditing system with geometry-based alerts that successfully identified impending model failure up to 7 epochs earlier than was evident from the validation loss curve. SentryCam's flexible framework is easily adaptable, supporting both the exploratory analysis and proactive auditing essential for robust model development. The code is available at https://github.com/xianglinyang/SentryCam. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15135 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Surveillance: Live-Update Visualization of Latent Training Dynamics Yang, Xianglin Dong, Jin Song Machine Learning Monitoring the inner state of deep neural networks is essential for auditing the learning process and enabling timely interventions. While conventional metrics like validation loss offer a surface-level view of performance, the evolution of a model's hidden representations provides a deeper, complementary window into its internal dynamics. However, the literature lacks a real-time tool to monitor these crucial internal states. To address this, we introduce SentryCam, a live-update visualization framework that tracks the progression of hidden representations throughout training. SentryCam produces high-fidelity visualizations of the evolving representation space with minimal latency, serving as a powerful dashboard for understanding how a model learns. We quantitatively validate the faithfulness of SentryCam's visualizations across diverse datasets and architectures (ResNet, ViT). Furthermore, we demonstrate SentryCam's practical utility for model auditing through a case study on training instability. We designed an automated auditing system with geometry-based alerts that successfully identified impending model failure up to 7 epochs earlier than was evident from the validation loss curve. SentryCam's flexible framework is easily adaptable, supporting both the exploratory analysis and proactive auditing essential for robust model development. The code is available at https://github.com/xianglinyang/SentryCam. |
| title | Neural Surveillance: Live-Update Visualization of Latent Training Dynamics |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.15135 |