Visual Ensemble Analysis to Study the Influence of Hyper-parameters on Training Deep Neural Networks
Sagad Hamid, Adrian Derstroff, Sören Klemm, Quynh Quang Ngo, Xiaoyi Jiang, Lars Linsen · Eurographics · 2019
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Eurographics · OpenAlex · article · 2019
Abstract
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.
Open the resolved locator · 10.2312/mlvis.20191160
Metadata licence: OpenAlex metadata (CC0)