University of Cambridge > Talks.cam > Foundation AI > Neural semantic reasoning for interpretable and rigorous logical reasoning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Neural semantic reasoning for interpretable and rigorous logical reasoning

Download to your calendar using vCal

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

LT1

In this seminar, I will motivate set-theoretic Neural Reasoning and present the first such neural network, the Sphere Neural Network, which achieves the rigour of symbolic-level Aristotelian syllogistic reasoning (the beginning of the history of logical reasoning) and its variants, through constructing a sphere configuration as an Euler diagram (semantic model). I will argue that, being limited by vector embeddings (spheres with zero radius), traditional Neural Reasoning (supervised deep learning) cannot achieve rigorous syllogistic reasoning. Thus, the ability to engage in rigorous syllogistic reasoning becomes the watershed between vector-based neural reasoning (using training data) and sphere-based neural reasoning (using set-theoretic semantics).  Neural semantic reasoning offers a new approach to developing interpretable and reliable neural networks.

This talk is part of the Foundation AI series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

in person & via zoom Philosophical Approaches to Education seminar series SS02, Computer Laboratory, William Gates Building

Other talks

Christopher Cowie on the epistemology of assessing biosignature claims Nature and law Morning Break Group Work Title to be confirmed Title to be confirmed
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity