SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model ParallelizationDownload PDFOpen Website

2017 (modified: 11 Nov 2022)ICML 2017Readers: Everyone
Abstract: We propose a novel deep neural network that is both lightweight and effectively structured for model parallelization. Our network, which we name as SplitNet, automatically learns to split the netwo...
0 Replies

Loading