CogRobo Seminar: Towards Tractable, Interpretable and Responsible AI
Vaishak Belle gave a seminar at the Sabancı University in Turkey on their recent work on interpretable and ethical AI.
Title: Towards Tractable, Interpretable and Responsible AI
Date/Time: June 20, 2019 / 13.40-14.30
Place: FENS L067
Abstract: Artificial Intelligence (AI) provides many opportunities to improve private and public life, and it has enjoyed significant investment in the UK, EU and elsewhere. Indeed, discovering patterns and structures in large troves of data in an automated manner is a core component of data science. Machine learning currently drives applications in computational biology, natural language processing and robotics. However, such a highly positive impact is coupled to a significant challenge: when can we convincingly deploy these methods in our workplace? For example, can we understand the decisions made by these automated systems? Can we provide prior knowledge and suggestions to the learning modules? And finally, should the automated system be held responsible for the decisions it takes? In this talk, we report on some recent progress in the field on these themes, especially covering some approaches touching on tractable learning.