Philosophy

PPIG: Philosophy, Psychology, and Informatics Group

Speaker: Alex Doumas (University of Edinburgh)

Title: Relation learning in a neurocomputational architecture supports cross-domain transfer

Abstract: People readily generalise prior knowledge to novel situations and stimuli. Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance in specific domains, but machine learning systems struggle to generalise information to untrained situations. We present and model that demonstrates human-like extrapolatory generalisation by learning and explicitly representing an open-ended set of relations characterising regularities within the domains it is exposed to. First, when trained to play one video game (e.g., Breakout). the model generalises to a new game (e.g., Pong) with different rules, dimensions, and characteristics in a single shot. Second, the model can learn representations from a different domain (e.g., 3D shape images) that support learning a video game and generalising to a new game in one shot. By exploiting well-established principles from cognitive psychology and neuroscience, the model learns structured representations without feedback, and without requiring knowledge of the relevant relations to be given a priori. We present additional simulations showing that the representations that the model learns support cross-domain generalisation. The model's ability to generalise between different games demonstrates the flexible generalisation afforded by a capacity to learn not only statistical relations, but also other relations that are useful for characterising the domain to be learned. In turn, this kind of flexible, relational generalisation is only possible because the model is capable of representing relations explicitly, a capacity that is notably absent in extant statistical machine learning algorithms.

Further information

We are a group of researchers from diverse backgrounds in the above-mentioned groups (and beyond) who aim to gain an interdisciplinary yet deep understanding of the threads that bind the human mind and the world. Please come along!

Can I be on the mailing list and send mails to the list?

Yes, you can. Just go to mailing list.

Contact details

Dr Alistair Isaac

Nov 13 2019 -

PPIG: Philosophy, Psychology, and Informatics Group

2019-11-13: Relation learning in a neurocomputational architecture supports cross-domain transfer

Room 1.20, Dugald Stewart Building, 3 Charles Street, Edinburgh, EH8 9AD