November 30th, 2022 
Daniela Lopez de Luise The Center for Robotics and Neural Systems (CRNS) is pleased to announce the talk of Dr. Dileep George from Google DeepMind – USA on Wednesday, November 30th from 3:00 PM to 4:30 PM (London time) over Zoom. Thank you for forwarding the invitation to any of your colleagues who might be interested.
>> Events: The CRNS talk series will cover a wide range of topics including social and cognitive robotics, computational neuroscience, computational linguistics, cognitive vision, machine learning, AI, and applications to healthcare. More details are available here:
>> Link for the next event (No Registration is Required):
Join Zoom Meeting
>> Title of the talk: Reverse engineering cortical microcircuit models of visual perception
Abstract:
Although deep learning has made tremendous strides in visual recognition and generation, a significant gap remains between human and machine perception. In this talk, I will argue that models that use stochastic variables, lateral interactions, and dynamic inference might be required to close this gap. I will then describe a generative model, Recursive Cortical Networks (RCN), that partially meets these requirements and demonstrated excellent performance on some visual task benchmarks.
Using RCN we derive a family of anatomically instantiated and functional cortical circuit models. Efficient inference and generalization guided the representational choices in the original computational model. The cortical circuit model is derived by systematically comparing the computational requirements of this model with known anatomical constraints. The derived model suggests precise functional roles for the feed-forward, feedback, and lateral connections observed in different laminae and columns, assigns a computational role for the path through the thalamus, predicts the interactions between blobs and interblobs, and offers an algorithmic explanation for the innate inter-laminar connectivity between clonal neurons within a cortical column. The model also explains several visual phenomena, including the subjective contour effect, and neon-color spreading effect, with circuit-level precision. Our work paves a new path forward in understanding the logic of cortical and thalamic circuits.
>> If you have any questions, please don't hesitate to contact me,
Regards
Posted in Congress Design by 2b Consult