Random synaptic feedback weights support error backpropagation for deep learning

The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by...

Celý popis

Podrobná bibliografie
Hlavní autoři: Lillicrap, T, Cownden, D, Tweed, D, Akerman, C
Médium: Journal article
Jazyk:English
Vydáno: Nature Publishing Group 2016