Description: Layer freezing is a neural network training technique that keeps selected layers’ parameters fixed to reduce computational cost or preserve learned representations.
2019 · Xueli Xiao, Thosini Bamunu Mudiyanselage, et al. · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · 59