Evolution under Length Constraints for CNN Architecture design

What is it about?

In recent years, the CNN architectures designed by evolution algorithms have proven to be competitive with handcrafted architectures designed by experts. However, these algorithms need a lot of computational power, which is beyond the capabilities of most researchers and engineers. To overcome this problem, we propose an evolution architecture under length constraints. It consists of two algorithms: a search length strategy to find an optimal space and a search architecture strategy based on genetic algorithm to find the best individual in the optimal space. Our algorithms reduce drastically resource cost and also keep good performance. On the Cifar-10 dataset, our framework presents outstanding performance with an error rate of 5.12% and only 4.6 GPU a day to converge to the optimal individual -22 GPU a day less than the lowest cost automatic evolutionary algorithm in the peer competition.

Featured Image

Photo by Markus Winkler on Unsplash

Photo by Markus Winkler on Unsplash

Why is it important?

NAS automatically finds the right architecture for our local data. However, they require enormous computational resources. The methods proposed have enabled us to drastically reduce the number of GPU days required to find the best architecture, while keeping the same performance.