DENSER: Deep Evolutionary Network Structured Representation

TL;DR

DENSER is a novel evolutionary algorithm that automatically designs neural network architectures and hyper-parameters, achieving state-of-the-art results on CIFAR-100 and competitive performance on other datasets.

Contribution

It introduces a two-level representation with human-readable grammar for automatic neural network design, combining topology search and hyper-parameter tuning.

Findings

Achieved 94.13% accuracy on CIFAR-10

Reported 78.75% accuracy on CIFAR-100

Networks outperform many manually designed CNNs

Abstract

Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology (e.g., number of layers, type of layers), but also tunes hyper-parameters, such as, learning parameters or data augmentation parameters. The automatic design is achieved using a representation with two distinct levels, where the outer level encodes the general structure of the network, i.e., the sequence of layers, and the inner level encodes the parameters associated with each layer. The allowed layers and range of the hyper-parameters values are defined by means of a human-readable Context-Free Grammar. DENSER was used to evolve ANNs for CIFAR-10, obtaining an average test accuracy of 94.13%. The networks evolved for the CIFA--10 are tested on the MNIST, Fashion-MNIST, and CIFAR-100; the results are highly competitive, and on the CIFAR-100 we report a test accuracy of 78.75%. To the best of our knowledge, our CIFAR-100 results are the highest performing models generated by methods that aim at the automatic design of Convolutional Neural Networks (CNNs), and are amongst the best for manually designed and fine-tuned CNNs.