A sparse auto-encoder called RandNet learns image dictionaries and classifies MNIST from random compressed measurements, reaching 1.56% test error at 50% compression.
G 0.1” stands for RandNet with Gaussian Φ andβ = 0.1. “S 0.5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RandNet: deep learning with compressed measurements of images
A sparse auto-encoder called RandNet learns image dictionaries and classifies MNIST from random compressed measurements, reaching 1.56% test error at 50% compression.