Thermodynamics modeling of deep learning systems for a temperature based filter pruning technique
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...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-05-01
|
Series: | Frontiers in Physics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1145156/full |
Summary: | 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. |
---|---|
ISSN: | 2296-424X |