Task and Explanation Network
This addresses the need for more interpretable AI systems, though it appears incremental as it builds on existing explainability concepts without specifying novel breakthroughs.
The paper tackles the problem of explainability in deep networks by proposing that AI systems should be tasked with both completing a task and providing an explanation for it, introducing the Task and Explanation Network (TENet) framework to integrate these aspects.
Explainability in deep networks has gained increased importance in recent years. We argue herein that an AI must be tasked not just with a task but also with an explanation of why said task was accomplished as such. We present a basic framework -- Task and Explanation Network (TENet) -- which fully integrates task completion and its explanation. We believe that the field of AI as a whole should insist -- quite emphatically -- on explainability.