Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets

01/25/2019
by   Guillaume Bellec, et al.
0

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 only late during a network computation, we enrich locally available information through feedforward eligibility traces of synapses that can easily be computed in an online manner. The resulting new generation of learning algorithms for recurrent neural networks provides a new understanding of network learning in the brain that can be tested experimentally. In addition, these algorithms provide efficient methods for on-chip training of RSNNs in neuromorphic hardware.

READ FULL TEXT
research
10/22/2020

Brain-Inspired Learning on Neuromorphic Substrates

Neuromorphic hardware strives to emulate brain-like neural networks and ...
research
03/12/2021

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

Inspired by more detailed modeling of biological neurons, Spiking neural...
research
07/15/2022

Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing

There is ample neurobiological evidence that context-sensitive neocortic...
research
06/28/2022

Short-Term Plasticity Neurons Learning to Learn and Forget

Short-term plasticity (STP) is a mechanism that stores decaying memories...
research
07/20/2019

Learning spatiotemporal signals using a recurrent spiking network that discretizes time

Learning to produce spatiotemporal sequences is a common task the brain ...
research
09/17/2019

Control of criticality and computation in spiking neuromorphic networks with plasticity

The critical state is assumed to be optimal for any computation in recur...
research
06/21/2012

A biological gradient descent for prediction through a combination of STDP and homeostatic plasticity

Identifying, formalizing and combining biological mechanisms which imple...

Please sign up or login with your details

Forgot password? Click here to reset