Topics of interest include but not limited to the following. Along with novel research work, we encourage submissions with demonstrations and case studies from real-life experiences.
What are the desiderata of building such hybrid knowledge injected neural networks?
How/where should the knowledge injection in neural networks happen to build efficient and scalable hybrid models?
How do we develop principled approaches for knowledge injection in deep learning/machine learning?
How can knowledge injection mitigate huge data dependence, bias/trust issues and improve explainability of deep learning systems?
How can knowledge injection help compensate the lack of implicit (or "tacit") human knowledge in AI systems?
How can the reconciliation of inherent NN knowledge acquired from data with the external structured knowledge happen?
How to ensure credibility, robustness and trustworthiness of external knowledge sources
What kind of knowledge representations, formal languages, and neural architectures facilitate efficient hybrid models?
What kind of deep learning applications would benefit from knowledge injection?
Design of Benchmarks and evaluation measures for KINN