A statistical mixture of Tanh and Swish activations with critical mixing fraction p_c induces a continuous phase transition to scale-invariant signal propagation in deep networks while preserving smoothness.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Chaos in higher-order coupled oscillator networks is organized by effective-frequency shear from amplitude heterogeneity, not by phase coherence.
Two termination criteria for transient phases in the Ginelli CLV algorithm are compared on two Hamiltonian systems, with an adaptation proposed to avoid alignment issues that degrade accuracy in center-subspace computations over long backward times.
citing papers explorer
-
Competing nonlinearities, criticality, and order-to-chaos transition in deep networks
A statistical mixture of Tanh and Swish activations with critical mixing fraction p_c induces a continuous phase transition to scale-invariant signal propagation in deep networks while preserving smoothness.
-
Shear, Not Coherence, Organizes chaotic response under Higher-Order Coupling
Chaos in higher-order coupled oscillator networks is organized by effective-frequency shear from amplitude heterogeneity, not by phase coherence.
-
On the efficient numerical computation of covariant Lyapunov vectors
Two termination criteria for transient phases in the Ginelli CLV algorithm are compared on two Hamiltonian systems, with an adaptation proposed to avoid alignment issues that degrade accuracy in center-subspace computations over long backward times.