Fast-DENSER: Fast Deep Evolutionary Network Structured Representation

This paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). The approach is known as Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) and is capable of simultaneously optimising the topology, learning strategy and any other required hyper-parameters (e.g., data pre-processing or augmentation). Fast-DENSER has been successfully applied to numerous object recognition tasks, with the generation of Convolutional Neural Networks (CNNs). The code is developed and tested in Python3, and made available as a library. A simple and easy to follow example is described for the automatic search of CNNs for the Fashion-MNIST benchmark. (C) 2021 The Authors. Published by Elsevier B.V.

Automated summary

This paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). Fast-DENSER optimizes the topology, learning strategy, and required hyper-parameters simultaneously for tasks like object recognition. The code is developed and tested in Python3, and a simple example for the automatic search of CNNs for the Fashion-MNIST benchmark is provided.