A forward-only Hebbian Hopfield classifier with per-class weight matrices and learned sparsity reaches 75.3% on binary MNIST under simulated oscillator inference, and up to 97.4% when its features are fed to a finetuned linear classifier.
Machine learning in healthcare
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.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification
A forward-only Hebbian Hopfield classifier with per-class weight matrices and learned sparsity reaches 75.3% on binary MNIST under simulated oscillator inference, and up to 97.4% when its features are fed to a finetuned linear classifier.