Assessing Architectural Similarity in Populations of Deep Neural Networks

Audrey G. Chung, Paul Fieguth, Alexander Wong; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the synthesis of increasingly efficient architectures over successive generations. Despite recent research showing the efficacy of multi-parent evolutionary synthesis, little has been done to directly assess architectural similarity between networks during the synthesis process for improved parent network selection. In this work, we present a preliminary study into quantifying architectural similarity via the percentage overlap of architectural clusters. Results show that networks synthesized using architectural alignment (via gene tagging) maintain higher architectural similarities within each generation, potentially restricting the search space of highly efficient network architectures.

Related Material


[pdf]
[bibtex]
@InProceedings{Chung_2019_CVPR_Workshops,
author = {Chung, Audrey G. and Fieguth, Paul and Wong, Alexander},
title = {Assessing Architectural Similarity in Populations of Deep Neural Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}