On the Efficiency of Convolutional Neural Networks

arXiv:2404.03617v1 Announce Type: new
Abstract: Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have used convnets to produce accurate results that were unachievable a decade ago. Yet computer scientists make computational efficiency their primary objective. Accuracy with exorbitant cost is not acceptable; an algorithm must also minimize its computational requirements. Confronted with the daunting computation that convnets use, deep learning researchers also became interested in efficiency. …

abstract accuracy alexnet arxiv computational computer convolutional neural networks cost cs.cv cs.lg deep learning efficiency networks neural networks performance researchers results scientists type vision vision models