University of Cambridge > > as2713's list > Abstraction and Analogy: The Keys to Robust Artificial Intelligence

Abstraction and Analogy: The Keys to Robust Artificial Intelligence

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact .

While AI has made dramatic progress over the last decade in areas such as vision, language processing, and robotics, current AI systems still lack key aspects of human intelligence. In this lecture I will argue that the inability to form conceptual abstractions—and to make abstraction-driven analogies—is a primary source of brittleness and unreliability in state-of-the-art AI systems. I will reflect on the role played by abstraction at all levels of intelligence and on the prospects for developing AI systems with humanlike abilities for abstract reasoning and analogy.

Melanie will be joined by two respondents who’ll offer thoughts from their perspectives on the talk to start the Q&A discussion.

The event is free to attend and available in person and online. You can sign up on Eventbrite in the link below:

This talk is part of the as2713's list series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity