<ul><li>PreNeT is a predictive framework designed to optimize the training time of deep learning models, particularly Transformer-based architectures.</li><li>It integrates comprehensive computational metrics, including layer-specific parameters, arithmetic operations, and memory utilization.</li><li>PreNeT accurately predicts training duration on various hardware infrastructures, including novel accelerator architectures.</li><li>Experimental results show that PreNeT achieves up to 72% improvement in prediction accuracy compared to contemporary frameworks.</li></ul>

PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time

Discover more