DeepRings: A Concentric-Ring Based Visualization to Understand Deep Learning Models

• Main Authors: Alves, Joao, Araujo, Tiago, Marques, Bernardo, Dias, Paulo, Santos, Beatriz Sousa
• Format: Conference Proceeding
• Language: English
• Subjects: Biological neural networks; Concentric Ring Design; Convolutional Neural Networks Feature Visualization; Critical infrastructure; Deep learning; Deep Learning Interpretability; Learning (artificial intelligence); Neurons; Task analysis; Visualization
• ISSN: 2375-0138
• DOI: 10.1109/IV51561.2020.00054

Artificial Intelligent (AI) techniques, such as ma-chine learning (ML), have been making significant progress over the past decade. Many systems have been applied in sensitive tasks involving critical infrastructures which affect human well-being or health. Before deploying an AI system, it is necessary to validate its behavior and guarantee that it will continue to perform as expected when deployed in a real-world environment. For this reason, it is important to comprehend specific aspects of such systems. For example, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images via feature visualization often focuses on explaining predictions for neurons of one single convolutional layer. Not presenting a global perspective over the features learned by the model leads the user to miss the bigger picture. In this work we focus on providing a representation based on the structure of deep neural networks. It presents a visualization able to give the user a global perspective over the feature maps of a convolutional neural network (CNN) in a single image, revealing potential problems of the learning representations present in the network feature maps.