Fixing layers beyond the effective depth, and transformer feedforward layers, to simplex ETFs gives nearly unchanged Fashion-MNIST accuracy with fewer parameters, though the method is underspecified.
Understanding intermediate layers using linear classifier probes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
Fixing layers beyond the effective depth, and transformer feedforward layers, to simplex ETFs gives nearly unchanged Fashion-MNIST accuracy with fewer parameters, though the method is underspecified.