Derives the asymptotic ratio of storage capacities between real-constrained and complex pre-activations in complex neural networks using Gardner volumes and the HCIZ formula.
High-dimensional manifold of solutions in neural networks: insights from statistical physics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A quantum perceptron with tunable-frequency oscillating activation achieves higher storage capacity than classical perceptrons, but the gain arises solely from the activation function form.
citing papers explorer
-
Shortcomings and capacities of real-constrained neural networks in complex spaces
Derives the asymptotic ratio of storage capacities between real-constrained and complex pre-activations in complex neural networks using Gardner volumes and the HCIZ formula.
-
Pseudo quantum advantages in perceptron storage capacity
A quantum perceptron with tunable-frequency oscillating activation achieves higher storage capacity than classical perceptrons, but the gain arises solely from the activation function form.