Visual Ensemble Analysis to Study the Influence of Hyper-parameters on Training Deep Neural Networks Article Swipe

View

Related Concepts

Artificial neural network Training (meteorology) Artificial intelligence Computer science Deep neural networks Machine learning Geography Meteorology

Sagad Hamid , Adrian Derstroff , Sören Klemm , Quynh Quang Ngo , Xiaoyi Jiang , Lars Linsen ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.2312/mlvis.20191160 · OA: W2965608405

A good deep neural network design allows for efficient training and high accuracy. The training step requires a suitable choice of several hyper-parameters. Limited knowledge exists on how the hyper-parameters impact the training process, what is the interplay of multiple hyper-parameters, and what is the interrelation of hyper-parameters and network topology. In this paper, we present a structured analysis towards these goals by investigating an ensemble of training runs.We propose a visual ensemble analysis based on hyper-parameter space visualizations, performance visualizations, and visualizing correlations of topological structures. As a proof of concept, we apply our approach to deep convolutional neural networks.