[visionlist] [meetings] CRNS Talk (11) - Live Talk by Dr. Dileep George - Google DeepMind, USA

Amir Aly amir.kalfat at gmail.com
Wed Mar 8 10:32:22 -04 2023

Dear All

* *Apologies for cross-posting**

The* Center for Robotics and Neural Systems* (CRNS) is pleased to announce
the talk of *Dr. **Dileep George* from *Google DeepMind *- USA on
Wednesday, *March 15th 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

Join our Cloud HD Video Meeting
Zoom is the leader in modern enterprise video communications, with an easy,
reliable cloud platform for video and audio conferencing, chat, and
webinars across mobile, desktop, and room systems. Zoom Rooms is the
original software-based conference room solution used around the world in
board, conference, huddle, and training rooms, as well as executive offices
and classrooms. Founded in 2011, Zoom helps businesses and organizations
bring their teams together in a frictionless environment to get more done.
Zoom is a publicly traded company headquartered in San Jose, CA.

>> *Title of the talk:  Reverse engineering cortical microcircuit models of
visual perception*


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,



*Dr. Amir Aly*

Lecturer in Artificial Intelligence and Robotics

Center for Robotics and Neural Systems (CRNS)

School of Engineering, Computing, and Mathematics

Room A307 Portland Square, Drake Circus, PL4 8AA

University of Plymouth, UK
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20230308/5f240667/attachment-0001.html>

More information about the visionlist mailing list