Texture Recognition Using a Biologically Plausible Spiking Phase-Locked Loop Model for Spike Train Frequency Decomposition
arxiv(2024)
摘要
In this paper, we present a novel spiking neural network model designed to
perform frequency decomposition of spike trains. Our model emulates neural
microcircuits theorized in the somatosensory cortex, rendering it a
biologically plausible candidate for decoding the spike trains observed in
tactile peripheral nerves. We demonstrate the capacity of simple neurons and
synapses to replicate the phase-locked loop (PLL) and explore the emergent
properties when considering multiple spiking phase-locked loops (sPLLs) with
diverse oscillations. We illustrate how these sPLLs can decode textures using
the spectral features elicited in peripheral nerves. Leveraging our model's
frequency decomposition abilities, we improve state-of-the-art performances on
a Multifrequency Spike Train (MST) dataset. This work offers valuable insights
into neural processing and presents a practical framework for enhancing
artificial neural network capabilities in complex pattern recognition tasks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要