Assessing Architectural Similarity in Populations of Deep Neural Networks

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
Gen No. Gene Tagging No Gene Tagging generations. However, little has been done to directly assess architectural similarity between networks during the synthesis process.
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.