Small-scale photonic KANs using four-parameter telecom nonlinear modules achieve 94.3% accuracy on classification and R²=0.986 on regression with few modules, approaching software baselines.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Koopman theory plus knowledge distillation yields linearized models from pre-trained nets that outperform standard least-squares Koopman approximations on MNIST and Fashion-MNIST in accuracy and stability.
A hybrid approach produces a simple circuit implementation of a bursting neuron from phase-locked loop equations.
Spin wave-based physical reservoir computing achieves 85.8% speaker classification accuracy without cochleagram preprocessing.
citing papers explorer
-
Extraction of linearized models from pre-trained networks via knowledge distillation
Koopman theory plus knowledge distillation yields linearized models from pre-trained nets that outperform standard least-squares Koopman approximations on MNIST and Fashion-MNIST in accuracy and stability.
-
Electronic Bursting Neuron: design, equations and hardware implementation
A hybrid approach produces a simple circuit implementation of a bursting neuron from phase-locked loop equations.
-
Spoken Digit Recognition and Speaker Classification by Nonlinear Interfered Spin Wave-Based Physical Reservoir Computing
Spin wave-based physical reservoir computing achieves 85.8% speaker classification accuracy without cochleagram preprocessing.