Deep Transparent Prediction through Latent Representation Analysis

Abstract

The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, unified way for prediction purposes. It is well known that DNNs are capable of analyzing complex data; however, they lack transparency in their decision making, in the sense that it is not straightforward to justify their prediction, or to visualize the features on which the decision was based. Moreover, they generally require large amounts of data in order to learn and become able to adapt to different environments. This makes their use difficult in healthcare, where trust and personalization are key issues. Transparency combined with high prediction accuracy are the targeted goals of the proposed approach. It includes both supervised DNN training and unsupervised learning of latent variables extracted from the trained DNNs. Domain Adaptation from multiple sources is also presented as an extension, where the extracted latent variable representations are used to generate predictions in other, non-annotated, environments. Successful application is illustrated through a large experimental study in various fields: prediction of Parkinson's disease from MRI and DaTScans; prediction of COVID-19 and pneumonia from CT scans and X-rays; optical character verification in retail food packaging.

16 pages, 8 figures, to be published at Foundations of Trustworthy AI integrating Learning, Optimisation and Reasoning (TAILOR) Workshop of European Conference on Artificial Intelligence (ECAI) 2020. arXiv admin note: substantial text overlap with arXiv:1911.10653

References in corpus (5)

• Learning Transferable Features with Deep Adaptation Networks
• Deep Visual Domain Adaptation: A Survey
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Clustering with Deep Learning: Taxonomy and New Methods
• A Scalable Test Suite for Continuous Dynamic Multiobjective Optimisation

Cited by in corpus (9)

• COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models
• Visual Transformer with Statistical Test for COVID-19 Classification
• Deep Learning Based Automated COVID-19 Classification from Computed Tomography Images
• COVID-19 Detection Using Transfer Learning Approach from Computed Tomography Images
• COVID Detection in Chest CTs: Improving the Baseline on COV19-CT-DB
• A hybrid deep learning framework for Covid-19 detection via 3D Chest CT Images
• A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images
• Custom Deep Neural Network for 3D Covid Chest CT-scan Classification
• 3D RegNet: Deep Learning Model for COVID-19 Diagnosis on Chest CT Image