MJKAN is a FiLM-modulated RBF layer that beats MLPs on some 1D regression tasks with carefully chosen basis counts, but underperforms MLPs on classification benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Bridging KAN and MLP: MJKAN, a Hybrid Architecture with Both Efficiency and Expressiveness
MJKAN is a FiLM-modulated RBF layer that beats MLPs on some 1D regression tasks with carefully chosen basis counts, but underperforms MLPs on classification benchmarks.