University of Cambridge > Talks.cam > Computational Neuroscience > Multitasking and compositionality in brain and in neural networks

  Browse A-Z

Log in

Googledetails Microsoftdetails

šŸ” Log In

Information on

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

ā„¹ļø Information

Multitasking and compositionality in brain and in neural networks

Download to your calendar using vCal

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

This talk will synthesize findings from two key papers that investigate the modular and compositional nature of neural computation. We will explore two distinct perspectives on how neural networks achieve flexible behavior in multitask settings by reusing learned computational primitives.

First, we will review Ito et al. 2022 (Compositional generalization through abstract representations in human and artificial neural networks), who used fMRI and a highly compositional task to identify abstract representations (i.e. orthogonalization) as a neural substrate for compositional generalization in humans. They demonstrated that pretraining artificial neural networks (ANNs) on basic task ā€œprimitivesā€ induces similar abstract representations, enabling zero-shot generalization and human-like performance.

Next, weā€™ll turn to the study by Driscoll et al., 2024 (Flexible multitask computation in recurrent networks utilizes shared dynamical motifs.) In this work, the authors show that primitives of neural computationā€”like attractors and decision boundariesā€”can arise naturally in a monolithic recurrent neural network, without being explicitly engineered for. Authors support this by locating and tracking attractors in the networkā€™s phase space, clustering tasks based on their neural activity, and demonstrating that simulated ā€œlesionsā€ selectively disrupt tasks in line with those clusters. We will take a critical look at these findings in our journal club, discussing the methodsā€™ applicability as well as their strengths and limitations.

This talk is part of the Computational Neuroscience series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Venue TBC in Cambridge The Senior Parlour, Magdalene College, Cambridge William Harvey Lecture Theatre

Other talks

Title to be confirmed title abstract tba Talk TBC Title to be confirmed Afternoon Break Morning Break / Group Photo
 

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