Time: 15.30-16.30
Date: Thursday 31 October
Location: In Person | I-X Conference Room | Level 5
Translation and Innovation Hub (I-HUB)
Imperial White City Campus
84 Wood Lane
London W12 0BZ
Eleonora Giunchiglia is a Lecturer at I-X and the Department of Electrical and Electronic Engineering. She completed her PhD at the University of Oxford in 2022, followed by a post-doctoral research position at TU Wien. She is also part of the Editorial Board of the Neuro-Symbolic AI journal and a junior member of the Future of Life Institute.
Ensuring Reliable Outcomes in Deep Learning: The Key Role of Requirements
Owing to their remarkable ability of finding hidden patterns in data, deep learning models have been extensively applied in many different domains. However, recent works have shown that neural networks often fail to comply with requirements expressing background knowledge about the problem at hand. This represents a major drawback for deep learning models, as compliance with requirements is a necessary condition for standard software deployment. In this talk we 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 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 present the core methodologies and techniques for deep learning with graph-structured data along with some recent advances and open problems.
