Sanjukta Krishnagopal presentation

Sanjukta Krishnagopal, postdoc at the Gatsby Computational Neuroscience Unit at University College London, will present "Extracting patterns from complex temporal data using higher-order networks and machine learning."

Abstract: Networks are a natural way to model time-varying interactions between elements in various systems, social, biological etc. First, I present a novel network-based model for subtyping heterogeneous co-evolving data, with application in identifying and predicting subtypes in diseases such as Parkinson's and Stroke. Specifically, I develop a multi-layer trajectory-based algorithm that predicts Parkinson's disease subtype and their genetic identifiers with ~70% accuracy five years in advance. Many real world systems, however, involve simultaneous interactions between more than two entities, which are not naturally captured in conventional pairwise networks, and that are best modeled through 'higher-order networks', or simplicial complexes, a rapidly growing field for data analysis. I develop a novel formalism of community detection in simplicial complexes, and I apply them to social networks, language networks, and also to study group dynamics and cooperation in Everest mountaineering expeditions. Lastly, I present an overview of my recent machine learning research involving investigations of how information is encoded in neural networks, and how these methods can be applied to signal separation and data analysis.

Bio: Sanjukta's research lies at the interface of network science, machine learning and complex systems, with the goal of using data to answer questions about real world social and biological systems. She received her PhD from the University of Maryland in Physics. She is currently a postdoc at the Gatsby Computational Neuroscience Unit at University College London where she also works with Google Deepmind. She develops interdisciplinary computational and theoretical tools, usually involving data. She has lived on 4 continents, and enjoys dancing, diving and hiking in her spare time.