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 Evolutionary Network Structured Representation (Fast-DENSER) capable simultaneously optimising topology, learning strategy any other required hyper-parameters (e.g., data pre-processing or augmentation). Fast-DENSER has been successfully applied to numerous object recognition tasks, with generation Convolutional (CNNs). code developed tested in Python3, made available library. A simple easy follow example described CNNs Fashion-MNIST benchmark.