Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks

Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations ar...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-07
Hauptverfasser:	Shomron, Gil, Banner, Ron, Moran Shkolnik, Weiser, Uri
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Activation Artificial neural networks Convolution Degradation Feature maps Lightweight Neural networks Tuning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!