Time: 14.00 – 15.00
Date: Thursday 18 July
Location: Hybrid Event | I-X Conference Room | Level 5
Translation and Innovation Hub (I-HUB)
Imperial White City Campus
84 Wood Lane
London W12 0BZ
This talk has been organised in partnership with the I-X Women in AI Network (IX-WAI). These events are open to everyone, regardless of gender, and we encourage all to attend for insightful discussions and workshops.
Any questions, please contact Andreas Joergensen (a.joergensen@imperial.ac.uk)
Professor Claudia Clopath leads the Computational Neuroscience Laboratory in the Bioengineering Department at Imperial College London. Her research focuses on learning and memory in neuroscience, using mathematical and computational tools to model synaptic plasticity. Claudia holds an MSc in Physics from EPFL and a PhD in Computer Science. She completed postdoctoral fellowships in neuroscience at Paris Descartes and Columbia University.
Using Machine Learning Tools to Study Learning and Adaption in the Brain
Animals use afferent feedback to rapidly correct ongoing movements in the presence of a perturbation. Repeated exposure to a predictable perturbation leads to behavioural adaptation that counteracts its effects. Primary motor cortex (M1) is intimately involved in both processes, integrating inputs from various sensorimotor brain regions to update the motor output. Here, we investigate whether feedback-based motor control and motor adaptation may share a common implementation in M1 circuits. We trained a recurrent neural network to control its own output through an error feedback signal, which allowed it to recover rapidly from external perturbations. Implementing a biologically plausible plasticity rule based on this same feedback signal also enabled the network to learn to counteract persistent perturbations through a trial-by-trial process, in a manner that reproduced several key aspects of human adaptation. Moreover, the resultant network activity changes were also present in neural population recordings from monkey M1. Online movement correction and longer-term motor adaptation may thus share a common implementation in neural circuits.
This talk discusses how large language models can be useful in a variety of interdisciplinary applications including work at Sussex on wildlife exploitation, propaganda and hate speech detection, and resource recommendation.
This talk will show how to build neural models that are not only guaranteed to be compliant with the given requirements over the output space, but are also able to learn from the background knowledge expressed by the requirements themselves and thus get better performance.
This talk will present the core methodologies and techniques for deep learning with graph-structured data along with some recent advances and open problems.
