Sup3r: A Semi-Supervised Algorithm for increasing Sparsity, Stability, and Separability in Hierarchy Of Time-Surfaces architectures

arXiv:2404.12402v1 Announce Type: new
Abstract: The Hierarchy Of Time-Surfaces (HOTS) algorithm, a neuromorphic approach for feature extraction from event data, presents promising capabilities but faces challenges in accuracy and compatibility with neuromorphic hardware. In this paper, we introduce Sup3r, a Semi-Supervised algorithm aimed at addressing these challenges. Sup3r enhances sparsity, stability, and separability in the HOTS networks. It enables end-to-end online training of HOTS networks replacing external classifiers, by leveraging semi-supervised learning. Sup3r learns class-informative patterns, mitigates confounding features, and …

abstract accuracy algorithm architectures arxiv capabilities challenges cs.ai cs.lg cs.ne data event extraction feature feature extraction hardware neuromorphic paper semi-supervised sparsity stability type