# Learned adaptive properties for mitigation of weight perturbations in embedded spiking networks

## TL;DR

This paper introduces a biologically inspired method to adapt neural networks in extreme environments, maintaining performance despite weight drift.

## Contribution

The novel contribution is a context-driven adaptation mechanism for spiking networks that recovers from synaptic weight perturbations.

## Key findings

- Adaptive voltage thresholds and time constants guided by a global context signal recover network performance after weight perturbations.
- The method works for image classification and spatiotemporal tracking tasks under noise and realistic memristive device perturbations.
- The approach is effective for recurrent networks but not feedforward ones, by modulating network-level dynamics.

## Abstract

Recent years have seen an increased importance of neural network inference in edge-based scenarios, which impose size and power constraints requiring novel computing devices. These same edge scenarios may require operating over long periods of time, or exposure to extreme environments, resulting in a drift of neural network weights that cause degraded performance. In searching for ways to develop neural network approaches that perform robustly under these conditions, we propose a biologically-inspired mechanism for the dynamic adaptation of within-neuron parameters that is guided by a global context signal carrying information about perturbations and variability in incoming stimuli. Specifically, we demonstrate that adaptive voltage thresholds or neuronal time constants, when informed by a global context signal, can enable network-level mechanisms to recover from perturbed synaptic weights. Consistent with prior literature, the context-modulated approach is effective for recurrent, but not feedforward networks, by modulating network level dynamics. We demonstrate this approach successfully recovers performance in image classification tasks and spatiotemporal tracking tasks under idealized and Gaussian noise as well as for realistic perturbations from a memristive device when exposed to ionizing radiation. Finally, we discuss how this approach enables the design of robust and energy-efficient neuromorphic systems that perform well, even in resource-constrained scenarios with extreme environments such as edge processing.