Close
UCL NeuroAI Talk Series | Dr Ida Momennejad
09 June 2021, 2:00 pm–3:00 pm
Event Information
Open to
- All
Availability
- Yes
Organiser
-
Sabrina Moxom – SLMS Research Coordination Office
About the event
NeuroAI is a series of themed talks organised by the UCL NeuroAI community. This month's speaker is Dr Ida Momennejad (Microsoft Research NYC).
Talk title- "Toward Human-like RL"
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
Dr Ida Momennejad
Senior Researcher at Microsoft Research, New York City
I am a Senior Researcher in Reinforcement Learning at Microsoft Research, New York City. Previously I was as an Associate Researcher in the Department of Biomedical Engineering at Columbia University, and before that a postdoc in computational neuroscience at Princeton University. I completed my PhD at Humboldt University in Berlin, Germany where I did my research at the Bernstein Center for Computational Neuroscience. I received my MSc degree in Philosophy of Science in Utrecht, the Netherlands, and my undergraduate degree in Software Engineering in Tehran, Iran.
My research interests are at the intersection of reinforcement learning and human cognition & behavior. I am excited about RL approaches to memory and planning. I’ve studied how humans build models of the environment and how this learning interacts with memory, exploration, & planning in both individual and multi-agent settings. I’ve tested some of these models using behavioral experiments, fMRI, and electrophysiology. Some recent projects I’m excited about include building more efficient models of memory, multi-agent simulations and metalearning, computational approaches to mental health, and RL agents with human-like navigation in games.
More about Dr Ida Momennejad