MetaSort: An Accelerated Approach for Non-uniform Compression and Few-shot Classification of Neural Spike Waveforms
This work aims to improve the efficiency and accuracy of spike sorting for neuroscientists and researchers working with neural data, potentially enabling ultra-low-power, on-chip implementations.
This paper introduces MetaSort, an algorithm that simultaneously addresses non-uniform compression and few-shot classification of neural spike waveforms. It achieves high-fidelity spike shape approximation using an adaptive level crossing algorithm and handles classification through latent feature representation and meta-transfer learning.
Many previous works in spike sorting study spike classification and compression independently. In this paper, a novel algorithm is proposed called MetaSort to address these two problems. To deal with compression, a novel adaptive level crossing algorithm is proposed to approximate spike shapes with high fidelity. Meanwhile, the latent feature representation is used to handle the classification problem. Besides, to guarantee MetaSort is robust and discriminative, the geometric information of data is exploited simultaneously in the proposed framework by meta-transfer learning. Empirical experiments with in-vivo spike data demonstrate that MetaSort delivers promising performance, highlighting its potential and motivating continued development toward an ultra-low-power, on-chip implementation.