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.
In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules
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.