BI 038 Máté Lengyel: Probabilistic Perception and Learning

Brain Inspired

Jun 19 2019 | NaN

00:00 / NaN

Show Notes

Show notes:

Máté’s Cambridge website.
He’s part of the Computational Learning and Memory Group there.
Here’s his webpage at Central European University.
A review to introduce his subsequent work:
- Statistically optimal perception and learning: from behavior to neural representations.
Related recent talks:
- Bayesian models of perception, cognition and learning – CCCN 2017.
- Sampling: coding, dynamics, and computation in the cortex (Cosyne 2018).

Other Episodes

Episode 0

May 08, 2019 • 01:18:36

BI 034 Tony Zador: How DNA and Evolution Can Inform AI

Show notes: Tony’s lab site, where there are links to his auditory decision making work and connectome work we discuss. Here are a few...

Episode 0

February 21, 2020 • 01:29:17

BI 061 Jörn Diedrichsen and Niko Kriegeskorte: Brain Representations

Jörn, Niko and I continue the discussion of mental representation from last episode with Michael Rescorla, then we discuss their review paper, Peeling The...

Episode 0

April 05, 2020 • 01:40:13

BI 065 Thomas Serre: How Recurrence Helps Vision

Thomas and I discuss the role of recurrence in visual cognition: how brains somehow excel with so few “layers” compared to deep nets, how...