Turn Down that Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron

TL;DR

This paper introduces a simplified neuromorphic neuron model that encodes signal-to-noise ratio at synapses, enabling robust learning of spike patterns even in noisy environments, suitable for digital hardware implementation.

Contribution

The paper presents the first neuron model to encode afferent SNR and learn spike patterns without complex math, enhancing neuromorphic hardware capabilities.

Findings

Successfully encodes afferent SNR in a simple neuron model

Learns spike patterns while dynamically weighing noisy inputs

Demonstrates robustness on noisy MNIST digit classification

Abstract

We have added a simplified neuromorphic model of Spike Time Dependent Plasticity (STDP) to the Synapto-dendritic Kernel Adapting Neuron (SKAN). The resulting neuron model is the first to show synaptic encoding of afferent signal to noise ratio in addition to the unsupervised learning of spatio temporal spike patterns. The neuron model is particularly suitable for implementation in digital neuromorphic hardware as it does not use any complex mathematical operations and uses a novel approach to achieve synaptic homeostasis. The neurons noise compensation properties are characterized and tested on noise corrupted zeros digits of the MNIST handwritten dataset. Results show the simultaneously learning common patterns in its input data while dynamically weighing individual afferent channels based on their signal to noise ratio. Despite its simplicity the interesting behaviors of the neuron model and the resulting computational power may offer insights into biological systems.