Knowledge-infused Deep Learning

Abstract

Deep Learning has shown remarkable success during the last decade for essential tasks in computer vision and natural language processing. Yet, challenges remain in the development and deployment of artificial intelligence (AI) models in real-world cases, such as dependence on extensive data and trust, explainability, traceability, and interactivity. These challenges are amplified in high-risk fields, including healthcare, cyber threats, crisis response, autonomous driving, and future manufacturing. On the other hand, symbolic computing with knowledge graphs has shown significant growth in specific tasks with reliable performance. This tutorial (a) discusses the novel paradigm of knowledge-infused deep learning to synthesize neural computing with symbolic computing (b) describes different forms of knowledge and infusion methods in deep learning, and (c) discusses application-specific evaluation methods to assure explainability and reasoning using benchmark datasets and knowledge-resources. The resulting paradigm of "knowledge-infused learning'' combines knowledge from both domain expertise and physical models. A wide variety of techniques involving shallow, semi-deep, and deep infusion will be discussed along with the corresponding intuitions, limitations, use cases, and applications. More details can be found \urlhttp://kidl2020.aiisc.ai/.