Turn Down that Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron
This is an incremental advancement for neuromorphic computing and neuroscience, offering a simpler model suitable for hardware implementation.
The paper tackled the problem of enabling a single spiking neuron model to encode afferent signal-to-noise ratio (SNR) and learn spatio-temporal spike patterns unsupervised, by adding a simplified STDP model to SKAN. Results on noise-corrupted MNIST digits showed it learns common patterns while dynamically weighting channels based on SNR, though no concrete numbers were provided.
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.