Document Type

Article

Version Deposited

Published Version

Publication Date

4-5-2024

Publication Title

AI

DOI

10.3390/ai5020023

Abstract

Deep learning (DL) models have achieved state-of-the-art performance in many domains. The interpretation of their working mechanisms and decision-making process is essential because of their complex structure and black-box nature, especially for sensitive domains such as healthcare. Visual analytics (VA) combined with DL methods have been widely used to discover data insights, but they often encounter visual clutter (VC) issues. This study presents a compact neural network (NN) view design to reduce the visual clutter in explaining the DL model components for domain experts and end users. We utilized clustering algorithms to group hidden neurons based on their activation similarities. This design supports the overall and detailed view of the neuron clusters. We used a tabular healthcare dataset as a case study. The design for clustered results reduced visual clutter among neuron representations by 54% and connections by 88.7% and helped to observe similar neuron activations learned during the training process.

Comments

Copyright 2024 by The Authors. AI is an Open Access journal published by MDPI, Basel, Switzerland.

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS