Episode · Nov 4, 2023
On the neural code - with Arvind Kumar
Theoretical Neuroscience Podcast · Episode 3 · 1 h 26 min
We use cookies for analytics.
Podcast, Theoretical Neuroscience Podcast, Episode 11
Hosted by Gaute Einevoll
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.
Links:
The podcast was recorded on February 24th, 2024 and lasts 1 hour and 30 minutes.