Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons
Deep Learning, Computational Neuroscience, Machine Learning and seminar by Dr Irina Higgins, Google Deepmind
Hosted by NeuroAI UCL
Wednesday 14:00–15:10 London (GMT+1)
Ended
Abstract
Irina is a research scientist at DeepMind, where she works in the Froniers team. Her work aims to bring together insights from the fields of neuroscience and physics to advance general artificial intelligence through improved representation learning. Before joining DeepMind, Irina was a British Psychological Society Undergraduate Award winner for her achievements as an undergraduate student in Experimental Psychology at Westminster University, followed by a DPhil at the Oxford Centre for Computational Neuroscience and Artificial Intelligence, where she focused on understanding the computational principles underlying speech processing in the auditory brain. During her DPhil, Irina also worked on developing poker AI, applying machine learning in the finance sector, and working on speech recognition at Google Research."" https://arxiv.org/pdf/2006.14304.pdf
Topics
Related seminars
- Video · 50 min · Mar 13, 2021Rufin VanRullen, Centre de Recherche Cerveau et Cognition (CERCO)
Hebbian Plasticity Supports Predictive Self-Supervised Learning of Disentangled Representations
Video · 59 min · May 4, 2022Manu Halvagal, Friedrich Miescher Institute for Biomedical ResearchDecoding the neural processing of speech
Video page · Mar 23, 2021Tobias Reichenbach, Friedrich-Alexander-UniversityMore on speech processing
More from NeuroAI UCL
All talksUnderstanding reward-guided learning using large-scale datasets
Jul 9, 2025Kim StachenfeldNeurobiological constraints on learning: bug or feature?
Jun 11, 2025Cian O’DonellUnderstanding reward-guided learning using large-scale datasets
May 14, 2025Kim StachenfeldRelating circuit dynamics to computation: robustness and dimension-specific computation in cortical dynamics
Apr 23, 2025Shaul Druckmann