BI 065 Thomas Serre: How Recurrence Helps Vision

April 05, 2020 01:40:13
BI 065 Thomas Serre: How Recurrence Helps Vision
Brain Inspired
BI 065 Thomas Serre: How Recurrence Helps Vision

Apr 05 2020 | 01:40:13

/

Show Notes

Thomas and I discuss the role of recurrence in visual cognition: how brains somehow excel with so few “layers” compared to deep nets, how feedback recurrence can underlie visual reasoning, how LSTM gate-like processing could explain the function of canonical cortical microcircuits, the current limitations of deep learning networks like adversarial examples, and a bit of history in modeling our hierarchical visual system, including his work with the HMAX model and interacting with the deep learning folks as convolutional neural networks were being developed.

Show Notes:

Other Episodes

Episode 0

November 29, 2022 01:22:27
Episode Cover

BI 154 Anne Collins: Learning with Working Memory

Check out my free video series about what's missing in AI and Neuroscience Support the show to get full episodes and join the Discord...

Listen

Episode 0

June 29, 2024 01:27:19
Episode Cover

BI 189 Joshua Vogelstein: Connectomes and Prospective Learning

Support the show to get full episodes and join the Discord community. Jovo, as you'll learn, is theoretically oriented, and enjoys the formalism of...

Listen

Episode 0

October 12, 2020 01:35:43
Episode Cover

BI 086 Ken Stanley: Open-Endedness

Ken and I discuss open-endedness, the pursuit of ambitious goals by seeking novelty and interesting products instead of advancing directly toward defined objectives. We...

Listen