Inferring neural activity before plasticity as a foundation for learning beyond backpropagation - Nature Neuroscience.
This paper introduces ‘prospective configuration’, a new principle for learning in neural networks, which differs from backpropagation and is more efficient in learning and more consistent with data on neural activity and behavior.
Read in full here:
https://www.nature.com/articles/s41593-023-01514-1
This thread was posted by one of our members via one of our news source trackers.