KASAM: Spline Additive Models for Function Approximation. (arXiv:2205.06376v1 [cs.LG])

Neural networks have been criticised for their inability to perform continual
learning due to catastrophic forgetting and rapid unlearning of a past concept
when a new concept is introduced. Catastrophic forgetting can be alleviated by
specifically designed models and training techniques. This paper outlines a
novel Spline Additive Model (SAM). SAM exhibits intrinsic memory retention with
sufficient expressive power for many practical tasks, but is not a universal
function approximator. SAM is extended with the Kolmogorov-Arnold
representation theorem to a …

approximation arxiv function spline