AUTHOR=Lapenna M. , Faglioni F. , Fioresi R. 

TITLE=Thermodynamics modeling of deep learning systems for a temperature based filter pruning technique

JOURNAL=Frontiers in Physics

VOLUME=11

YEAR=2023

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1145156

DOI=10.3389/fphy.2023.1145156

ISSN=2296-424X

ABSTRACT=<p>We analyse the dynamics of convolutional filters’ parameters of a convolutional neural networks during and after training, via a thermodynamic analogy which allows for a sound definition of temperature. We show that removing high temperature filters has a minor effect on the performance of the model, while removing low temperature filters influences majorly both accuracy and loss decay. This result could be exploited to implement a temperature-based pruning technique for the filters and to determine efficiently the crucial filters for an effective learning.</p>