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

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

Update: 2024-04-271
Share

Description

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.  

Comments 
In Channel
loading
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

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

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