What does a digital research infrastructure for artificial intelligence look like? We are investigating this so that we can work towards new and improved components of a digital research infrastructure.
DIANNA: Deep Insight And Neural Network Analysis
SURF and the Netherlands eScience Center join forces to develop DIANNA: a standardized open source system that will ‘explain’ how Deep Neural Networks reason.
Acceptance of Deep Neural Networks
Modern scientific challenges are more and more tackled using Artificial Intelligence, usually with (Deep) Neural Networks (DNN). Despite their high predictive accuracy, the outcomes of Artificial Intelligence (AI) models, usually Deep Neural Networks (DNNs), are difficult to explain. This has earned them the reputation for being ‘black boxes’. Explainability, however, is necessary to foster trust and social acceptance. Although various methods to achieve explainable AI exist, they suffer from several drawbacks, and they are used mostly by AI experts rather than the wider scientific community.
Deep Insight And Neural Network Analysis
DIANNA stands for ‘Deep Insight And Neural Network Analysis’. This project aims at creating an open source software tool that ’explains’ how DNNs reason. The ‘explanation’ represents knowledge captured by the AI system which is visualized through a ‘relevance heatmap’. In this way the visualization itself can become a source of new scientific insight.
Best explainable AI methods for research
DIANNA aims to determine the best explainable AI (XAI) methods for use in research. It supports the Open Neural Network eXchange (ONNX) standard and provides new image benchmarks suited for studying the XAI heatmaps. To make DIANNA known and accessible to the wider research community, the Netherlands eScience Center and SURF will provide tutorials and future web demonstrators.
Showcasing the capabilities of DIANNA
The capabilities of DIANNA will be showcased on a radiology case. One of the challenges in planning radiotherapy treatment is how to deal with daily variations in the internal patient anatomy. Generating CT scans can potentially be used to simulate these variations. Obtaining explanations about the factors influencing the variations could help medical experts in their decision making.
DIANNA is a so-called SURF Alliance Project, an annual collaboration between the Netherlands eScience Center and SURF. The projects are primarily intended to connect advanced technological expertise within both organizations, based on their respective technology strategies. The software solutions resulting from the projects can potentially be reused to address other research problems in different disciplines.