Sveriges mest populära poddar
Theoretical Neuroscience Podcast
VetenskapLife Science

On synaptic learning rules for spiking neurons - with Friedemann Zenke - #11

1 tim 31 min•27 april 2024

Today's AI is largely based on supervised learning of neural networks using the backpropagation-of-error synaptic learning rule. This learning rule relies on differentiation of continuous activation functions and is thus not directly applicable to spiking neurons.

Today's guest has developed the algorithm SuperSpike to address the problem. He has also recently developed a biologically more plausible learning rule based on self-supervised learning. We talk about both.  

Fler avsnitt av Theoretical Neuroscience Podcast

Visa alla avsnitt av Theoretical Neuroscience Podcast
On modeling neural population activity with mean-field models - with Tilo Schwalger - #39
•2 tim 19 min
On extracting spiking network models from experiments - with Richard Gao - #38
•1 tim 36 min
On reproducibility of modeling and 10 years with the Potjans-Diesmann network model - with Hans Ekkehard Plesser - #37
•1 tim 29 min
On low-dimensional manifolds in motor cortex - with Sara Solla - #36
•2 tim 5 min
On modeling metabolic networks in the brain – with Polina Shichkova - #35
•1 tim 32 min
On balanced neural networks - with Nicolas Brunel - #34
•1 tim 39 min
On computational neurotechnology for the clinic - with Anthony Burkitt, Nada Yousif & Esra Neufeld - #33
•1 tim 1 min
On IIT and adversarial testing of consciousness theories - with Christof Koch - #32
•2 tim 18 min
On how to cure brain diseases - with Nicole Rust - #31
•2 tim 13 min
On co-dependent excitatory and inhibitory plasticity - with Tim Vogels - #30
•1 tim 31 min

Theoretical Neuroscience Podcast med Gaute Einevoll finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.