DeepAI
Log In Sign Up

Control of criticality and computation in spiking neuromorphic networks with plasticity

09/17/2019
by   Benjamin Cramer, et al.
0

The critical state is assumed to be optimal for any computation in recurrent neural networks, because criticality maximizes a number of abstract computational properties. We challenge this assumption by evaluating the performance of a spiking recurrent neural network on a set of tasks of varying complexity at - and away from critical network dynamics. To that end, we developed a spiking network with synaptic plasticity on a neuromorphic chip. We show that the distance to criticality can be easily adapted by changing the input strength, and then demonstrate a clear relation between criticality, task-performance and information-theoretic fingerprint. Whereas the information-theoretic measures all show that network capacity is maximal at criticality, this is not the case for performance on specific tasks: Only the complex, memory-intensive task profits from criticality, whereas the simple tasks suffer from it. Thereby, we challenge the general assumption that criticality would be beneficial for any task, and provide instead an understanding of how the collective network state should be tuned to task requirement to achieve optimal performance.

READ FULL TEXT
05/24/2020

Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks

The emergence of brain-inspired neuromorphic computing as a paradigm for...
01/16/2016

Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardware

In recent years the field of neuromorphic low-power systems that consume...
09/11/2020

P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware

Backpropagation algorithms on recurrent artificial neural networks requi...
06/17/2015

Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

Neuromorphic chips embody computational principles operating in the nerv...
04/20/2018

On the ground state of spiking network activity in mammalian cortex

Electrophysiological recordings of spiking activity are limited to a sma...
06/29/2017

Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines

In the past three decades, many theoretical measures of complexity have ...