Assessing Architectural Similarity in Populations of Deep Neural Networks
This is an incremental study for evolutionary deep intelligence, addressing parent network selection in multi-parent synthesis.
The study tackled the problem of assessing architectural similarity in deep neural networks during evolutionary synthesis, finding that networks synthesized with architectural alignment maintain higher similarity within generations, potentially restricting the search for efficient architectures.
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.