Close
UCL NeuroAI Talk Series | Benigno Uría
13 January 2021, 2:00 pm–3:00 pm
'The Spatial Memory Pipeline: a deep learning model of egocentric to allocentric understanding in mammalian brains'
Event Information
Open to
- All
Availability
- Yes
Organiser
-
Sabrina Moxom – SLMS Research Coordination Office
NeuroAI is a series of themed talks organised by the UCL NeuroAI community. This month's speaker is Benigno Uría (Google DeepMind).
About NeuroAI
The last decade has seen phenomenal advances in the field of machine learning (AI) (e.g. deep learning, reinforcement learning). Such is the change that no area of science can afford to ignore it, least of all neuroscience.
Crucially, AI shares a common lineage with neuroscience, and provides a means to emulate neural functions and the circuits supporting them, delivering a normative understanding of the brain and cognition (e.g. Banino et al., 2018; Stringer et al. 2019; Dabney et al., 2020).
Equally AI tools provide a means to discover, segment, and track distinct neural and behavioural states (e.g. Mathis et al., 2018; Frey et al., 2019) - yielding more efficient experiments and accelerating the pace of discovery. In turn, this understanding feeds back into the design of more effective AI architectures and models (e.g. Sabour et al., 2017; Stringer et al, 2019, Dabney et al., 2020).
Essentially, AI problems posed in neuroscience both require and inspire further advances in AI.
About the Speaker
Benigno Uría
Research Scientist at Google DeepMind
My name is Benigno Uría. I've been a research scientist at Google DeepMind since 2015. Before that I did my PhD at University of Edinburgh, where I had the privilege of being advised by Iain Murray and Steve Renals, and the honour of being mentored by John Bridle (Apple).
My research interest lies in the artificial intelligence field, more especifically in machine learning. During my PhD I studied the use of artificial neural networks for modelling the probabilistic relationship between large sets of variables. My work extended the NADE (neural autoregressive distribution estimator) model to real-valued data, and later leveraged the use of deep learning for improving its statistical performance.
The practical side of my PhD dealt with speech processing: speech recognition, synthesis and articulatory inversion. Some of which was used in popular portable devices.
More recently, after joining DeepMind, my research has focused on accelerating reinforcement learning by combining non-parametric techniques with deep neural networks.