Large-Scale Evolution of Image Classifiers
This work addresses the problem of reducing human effort in neural architecture design for image classification, though it is incremental as it builds on existing evolutionary methods.
The paper tackled the challenge of designing neural network architectures for image classification by using evolutionary algorithms to automatically discover models, achieving accuracies of 94.6% on CIFAR-10 and 77.0% on CIFAR-100 without human intervention.
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% (95.6% for ensemble) and 77.0%, respectively. To do this, we use novel and intuitive 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.