NEFeb 18, 2019

Evolutionary Neural AutoML for Deep Learning

arXiv:1902.06827v3120 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of making DNNs more accessible and efficient for users in commercial and research settings, though it is incremental by extending AutoML with evolutionary methods.

The paper tackles the difficulty of configuring deep neural networks (DNNs) by introducing LEAF, an evolutionary AutoML framework that optimizes hyperparameters, architectures, and network size, achieving state-of-the-art performance on medical image classification and natural language analysis with minimal performance drop when minimizing networks.

Deep neural networks (DNNs) have produced state-of-the-art results in many benchmarks and problem domains. However, the success of DNNs depends on the proper configuration of its architecture and hyperparameters. Such a configuration is difficult and as a result, DNNs are often not used to their full potential. In addition, DNNs in commercial applications often need to satisfy real-world design constraints such as size or number of parameters. To make configuration easier, automatic machine learning (AutoML) systems for deep learning have been developed, focusing mostly on optimization of hyperparameters. This paper takes AutoML a step further. It introduces an evolutionary AutoML framework called LEAF that not only optimizes hyperparameters but also network architectures and the size of the network. LEAF makes use of both state-of-the-art evolutionary algorithms (EAs) and distributed computing frameworks. Experimental results on medical image classification and natural language analysis show that the framework can be used to achieve state-of-the-art performance. In particular, LEAF demonstrates that architecture optimization provides a significant boost over hyperparameter optimization, and that networks can be minimized at the same time with little drop in performance. LEAF therefore forms a foundation for democratizing and improving AI, as well as making AI practical in future applications.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes