Dynamic Switch Layers For Unsupervised Learning

arXiv:2404.04405v1 Announce Type: new
Abstract: On-device machine learning (ODML) enables intelligent applications on resource-constrained devices. However, power consumption poses a major challenge, forcing a trade-off between model accuracy and power efficiency that often limits model complexity. The previously established Gated Compression (GC) layers offer a solution, enabling power efficiency without sacrificing model performance by selectively gating samples that lack signals of interest. However, their reliance on ground truth labels limits GC layers to supervised tasks. This work introduces the Dynamic …

abstract accuracy applications arxiv challenge complexity compression consumption cs.lg devices dynamic efficiency enabling however intelligent machine machine learning major model accuracy performance power power consumption solution trade trade-off type unsupervised unsupervised learning