Mazlum Ferhat Arslan

Neuromanifold-Regularized KANs for Shape-fair Feature Representations

Traditional deep networks struggle to acquire shape-fair representations due to their high expressivity. Kolmogorov-Arnold Networks (KANs) are promising candidates as they learn nonlinearities directly, a property that makes them more adaptive. However, KANs perform suboptimally in terms of shape-fa…