Hopfield network dynamics are recast as natural gradient descent with an activation-dependent Riemannian metric, and as a Wasserstein gradient flow in the probability-measure space for the stochastic diffusion machine.
Dual Hopfield methods for large-scale mixed-integer programming
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hopfield Neural Network Flow: A Geometric Viewpoint
Hopfield network dynamics are recast as natural gradient descent with an activation-dependent Riemannian metric, and as a Wasserstein gradient flow in the probability-measure space for the stochastic diffusion machine.