Along with the success of deep learning, there is concern about the opacity, transparency and trustworthiness of these models. Because of this concern, many critical applications of deep learning models are hindered or delayed. The concern is so high that it is now a major research focus in Artificial Intelligence (AI) at funding agencies like DARPA and NSF (DARPA: Explainable Artificial Intelligence (XAI)). The public uproar against non-transparent models is also widespread. Here are two quotes from recent articles.

Harvard Business Review 2019 - We Need AI That Is Explainable, Auditable, and Transparent: “First, AI systems must be subjected to vigorous human review….Third, AI systems, and the data sources used to train them, need to be transparent and available for audit….We wouldn’t find it acceptable for humans to be making decisions without any oversight, so there’s no reason why we should accept it when machines make decisions.”

Forbes 2019 - Explainable AI: Why We Need To Open The Black Box: “In highly regulated, high-risk/high-value industries, there's simply too much at stake to trust the decisions of a machine at face value, with no understanding of a machine’s reasoning or the potential risks associated with a machine’s recommendations. These enterprises are increasingly demanding explainable AI (XAI).”

If we can make deep learning models explainable, transparent and trustworthy, the economic impact of such a technology would be in the trillions of dollars worldwide.

INNS is proud to devote its inaugural Virtual Technical Event (spanning workshops, tutorials, discussions and so on) to this important research topic. We invited some of the world’s leading scientists in the artificial neural network and deep learning fields to discuss this issue and offer new perspectives.

Call For Proposals

For details on submitting proposals of future virtual events, please visit https://www.inns.org/virtual-technical-events.