Search Results for author:
Found 2 papers, 1 papers with code
Exploring the Evolution of Hidden Activations with Live-Update Visualization
Monitoring the training of neural networks is essential for identifying potential data anomalies, enabling timely interventions and conserving significant computational resources.
DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
Moreover, our case study shows that our visual solution can well reflect the characteristics of various training scenarios, showing good potential of DVI as a debugging tool for analyzing deep learning training processes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
