Numerical simulations of a thermal deep learning machine on MNIST show solid layers near the boundaries, liquid layers in the middle, and a solid-depth that grows roughly as the logarithm of the data-to-width ratio.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Liquid and solid layers in a thermal deep learning machine
Numerical simulations of a thermal deep learning machine on MNIST show solid layers near the boundaries, liquid layers in the middle, and a solid-depth that grows roughly as the logarithm of the data-to-width ratio.