Fully-connected networks trained on images with two equally valid class cues systematically learn the low-level statistical pattern and ignore the symbolic code, unless the pattern is partially corrupted.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Feature selection of neural networks is skewed towards the less abstract cue
Fully-connected networks trained on images with two equally valid class cues systematically learn the low-level statistical pattern and ignore the symbolic code, unless the pattern is partially corrupted.