Can I read Biologically Inspired Alternatives to Backpropagation Through Time for Learning in Recurrent Neural Nets on EtoBox?

Biologically Inspired Alternatives to Backpropagation Through Time for Learning in Recurrent Neural Nets by Bellec, Guillaume; Scherr, Franz; Hajek, Elias; Salaj, Darjan; Legenstein, Robert; Maass, Wolfgang is a scholarly article available to read on EtoBox.

What is Biologically Inspired Alternatives to Backpropagation Through Time for Learning in Recurrent Neural Nets about?

The way how recurrently connected networks of spiking neurons in the brain acquire powerful information processing capabilities through learning has remained a mystery. This lack of understanding is linked to a lack of learning algorithms for recurrent networks of spiking neurons (RSNNs) that are both functionally powerful and can be implemented by known biological mechanisms. Since RSNNs are simultaneously a primary target for implementations of brain-inspired circuits in neuromorphic hardware, this lack of algorithmic insight also hinders technological progress in that area. The gold standard for learning in recurrent neural networks in machine learning is back-propagation through time (BPTT), which implements stochastic gradient descent with regard to a given loss function. But BPTT is unrealistic from a biological perspective, since it requires a transmission of error signals backwards in time and in space, i.e., from post- to presynaptic neurons. We show that an online merging of locally available information during a computation with suitable top-down learning signals in real-time provides highly capable approximations to BPTT. For tasks where information on errors arises onl

Author

Bellec, Guillaume; Scherr, Franz; Hajek, Elias; Salaj, Darjan; Legenstein, Robert; Maass, Wolfgang

Published

2019

Language

EN