Fast-DENSER: Fast Deep Evolutionary Network Structured Representation
Abstract
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.
- Publication:
-
SoftwareX
- Pub Date:
- June 2021
- DOI:
- 10.1016/j.softx.2021.100694
- Bibcode:
- 2021SoftX..1400694A
- Keywords:
-
- Artificial Neural Networks;
- Automated machine learning;
- NeuroEvolution