Results (1)
Search Parameters:
Author/Affiliation: Shannon GibbsOpen AccessArticle
13 Pages, 1,578 KB 
StradNet: Automated Structural Adaptation for Efficient Deep Neural Network Design
Abstract:
Deep neural networks (DNNs) have demonstrated remarkable success across a wide range of machine learning tasks. However, determining an effective network architecture, particularly the sizes of the hidden layers, remains a significant challenge and often relies on inefficient trial-and-error experimentation. In this paper, we propose an automated architecture design approach based on structurally adaptive DNNs,…
Read More(This article belongs to the SP19 (Special Issue on Innovation in Computing, Engineering Science & Technology 2025-26) & Section Artificial Intelligence in Computer Science (CAI))