UCL NeuroAI Talk Series | Professor Michael Milford

About the event

NeuroAI is a series of themed talks organised by the UCL NeuroAI community. This month's speaker is Professor Michael Milford (Queensland University of Technology).

Title: Spatial and Perceptual Neuroscience Questions a Roboticist Would Love to Have Answered

Brief abstract: I’ll give a brief overview of nearly two decades of our navigation, mapping and positioning research spanning robotics, computational neuroscience, machine learning and computer vision, and touch on the current capabilities and limitations of robotic systems. I’ll then use this foundation to go through a number of existing topics in spatial and perceptual neuroscience I, as a roboticist, would love to have neuroscientists and others shed more light on, and why they may help transform robotics and even lead to further insights for neuroscientists.

All other upcoming talks can be found here.

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.