Abstract:Training neural networks is difficult to interpret, particularly for newcomers. We introduce NeuroViz, an interactive visualization tool that supports real-time exploration of fully connected neural network training. Users can configure network architecture, activation functions, learning rates, and datasets, then observe activations, weight updates, and loss progression. NeuroViz visualizes weight changes in direct correspondence with activation signals in both forward and backward passes, enabling users to distinguish pre- and post-update states within individual epochs and view dynamically updating per-neuron equations. We conduct a comparative user study with 31 participants against six established visualization tools and we achieved the highest usability score (SUS 80.97, in the 'excellent' range), with mean rankings of 2.47 for clarity and 2.23 for usefulness (lower is better). Over 70% of participants reported that the visualizations substantially increased their perception of neural network training transparency. The implemented instance is accessible at this https URL.
| Comments: | 9 pages, 4 figures, 6 tables |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | H.5.2; I.2.6 |
| Cite as: | arXiv:2605.02044 [cs.LG] |
| (or arXiv:2605.02044v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02044 arXiv-issued DOI via DataCite (pending registration) |
From: Tanvi Sharma [view email]
[v1]
Sun, 3 May 2026 20:26:09 UTC (1,981 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。