Large-Scale Evolution of Image Classifiers

03/03/2017
by   Esteban Real, et al.
0

Neural networks have proven effective at solving difficult problems but designing their architectures can be challenging, even for image classification problems alone. Our goal is to minimize human participation, so we employ evolutionary algorithms to discover such networks automatically. Despite significant computational requirements, we show that it is now possible to evolve models with accuracies within the range of those published in the last year. Specifically, we employ simple evolutionary techniques at unprecedented scales to discover models for the CIFAR-10 and CIFAR-100 datasets, starting from trivial initial conditions and reaching accuracies of 94.6 ensemble) and 77.0 mutation operators that navigate large search spaces; we stress that no human participation is required once evolution starts and that the output is a fully-trained model. Throughout this work, we place special emphasis on the repeatability of results, the variability in the outcomes and the computational requirements.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/21/2018

Lamarckian Evolution of Convolutional Neural Networks

Convolutional neural networks belong to the most successul image classif...
research
09/10/2018

Finding Better Topologies for Deep Convolutional Neural Networks by Evolution

Due to the nonlinearity of artificial neural networks, designing topolog...
research
08/20/2018

A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification

Convolutional Neural Networks (CNNs) have demonstrated their superiority...
research
02/12/2023

Sparse Mutation Decompositions: Fine Tuning Deep Neural Networks with Subspace Evolution

Neuroevolution is a promising area of research that combines evolutionar...
research
10/12/2018

Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms

In this paper, we review the state-of-the-art results in evolutionary co...
research
03/06/2020

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch

Machine learning research has advanced in multiple aspects, including mo...
research
02/05/2018

Regularized Evolution for Image Classifier Architecture Search

The effort devoted to hand-crafting image classifiers has motivated the ...

Please sign up or login with your details

Forgot password? Click here to reset