Jim DiCarlo's guest appearances

Jim DiCarlo

Brain Inspired

James FitzGerald

Jessica Thompson

David Rosen

Ryan Poplin

Blake Richards

Terrence Sejnowski

David Ferrucci

Raia Hadsell

Melanie Mitchell

Matt Smith

Alison Gopnik

Brian Christian

Robert Wilson

Anil Seth

Jeff Hawkins

OwlTail

Jim and I discuss his reverse engineering approach to visual intelligence, using deep models optimized to perform object recognition tasks. We talk about the history of his work developing models to match the neural activity in the ventral visual stream, how deep learning connects with those models, and some of his recent work: adding recurrence to the models to account for more difficult object recognition, using unsupervised learning to account for plasticity in the visual stream, and controlling neural activity  by creating specific images for subjects to view. Notes: The DiCarlo Lab at MIT.Related papers:Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks.Fast recurrent processing via ventral prefrontal cortex is needed by the primate ventral stream for robust core visual object recognition.Unsupervised changes in core object recognition behavioral performance are accurately predicted by unsupervised neural plasticity in inferior temporal cortex.Neural population control via deep image synthesis.

<p>Jim and I discuss his reverse engineering approach to visual intelligence, using deep models optimized to perform object recognition tasks. We talk about the history of his work developing models to match the neural activity in the ventral visual stream, how deep learning connects with those models, and some of his recent work: adding recurrence to the models to account for more difficult object recognition, using unsupervised learning to account for plasticity in the visual stream, and controlling neural activity  by creating specific images for subjects to view.</p> <p>Notes:</p> <ul><li><a href="http://dicarlolab.mit.edu/" rel="nofollow" target="_blank">The DiCarlo Lab at MIT</a>.</li><li>Related papers:<ul><li><a href="https://mcgovern.mit.edu/wp-content/uploads/2019/01/7255.full_.pdf" rel="nofollow" target="_blank">Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks</a>.</li><li><a href="https://www.biorxiv.org/content/10.1101/2020.05.10.086959v1" rel="nofollow" target="_blank">Fast recurrent processing via ventral prefrontal cortex is needed by the primate ventral stream for robust core visual object recognition</a>.</li><li><a href="https://www.biorxiv.org/content/10.1101/2020.01.13.900837v1" rel="nofollow" target="_blank">Unsupervised changes in core object recognition behavioral performance are accurately predicted by unsupervised neural plasticity in inferior temporal cortex</a>.</li><li><a href="http://science.sciencemag.org/cgi/rapidpdf/364/6439/eaav9436?ijkey=iBRdlniG7iYuA&amp;keytype=ref&amp;siteid=sci" rel="noreferrer noopener nofollow" target="_blank">Neural population control via deep image synthesis.</a></li></ul></li></ul>

BI 075 Jim DiCarlo: Reverse Engineering Vision