What's Hidden in a Randomly Weighted Neural Network?

Training a neural network is synonymous with learning the values of the weights. By contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achieve impressive performance without ever training the weight values... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet Wide ResNet-50 (edge-popup) Top 1 Accuracy 73.3% # 137
Number of params 20.6M # 47

Methods used in the Paper