A researcher from the University of Central Florida has recently received funding from the U.S. Department of Energy (DOE) to further the human understanding of artificial intelligence (AI) reasoning. The $400,000 grant will fund the development of algorithms to create robust, multi-modal explanations for foundation AI models.
The project, which was one of 22 selected for the DOE’s 2022 Exploratory Research for Extreme-Scale Science (EXPRESS) grant, aims to create explanations for an AI model’s decision-making so that AI systems can be deployed with higher levels of human trust and understanding.
The grant will also be used to explore several novel explainable AI methods, working towards providing meaningful explanations for foundation AI models. Unlike task-specific models, foundation models are trained with a large set of data and can be applied to different tasks, making them a vital part of the AI industry.
The grant is the latest sign of the importance of explainable AI, with more and more organisations recognising the need for meaningful explanations of AI decisions. Through the use of this grant, the researcher from the University of Central Florida hopes to further the human understanding of AI reasoning, enabling the AI industry to continue to develop and innovate.