paper-with-me

홈 › Papers

KASAM: Spline Additive Models for Function Approximation

2022-05-12 · Heinrich van Deventer, Pieter Janse van Rensburg, Anna Bosman

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 novel universal function approximator, called the Kolmogorov-Arnold Spline Additive Model - KASAM. The memory retention, expressive power and limitations of SAM and KASAM are illustrated analytically and empirically. SAM exhibited robust but imperfect memory retention, with small regions of overlapping interference in sequential learning tasks. KASAM exhibited greater susceptibility to catastrophic forgetting. KASAM in combination with pseudo-rehearsal training techniques exhibited superior performance in regression tasks and memory retention.

📄 PDF Abstract BibTeX arXiv:2205.06376

Code (1)

hpdeventer/kasam 공식 구현 tf

Tasks

Additive modelsContinual Learning

Similar Papers 제목 키워드 기반

Saturating Splines and Feature Selection

2016-09-21 · Nicholas Boyd, Trevor Hastie, Stephen Boyd, Benjamin Recht 외

We extend the adaptive regression spline model by incorporating saturation, the natural requirement that a function extend as a constant outside a certain range. We fit saturating splines to data using a convex optimizat…

Additive modelsfeature selection

A comparison of deep networks with ReLU activation function and linear spline-type methods

2018-04-06 · Konstantin Eckle, Johannes Schmidt-Hieber

Deep neural networks (DNNs) generate much richer function spaces than shallow networks. Since the function spaces induced by shallow networks have several approximation theoretic drawbacks, this explains, however, not ne…

Automatic knot selection in smooth additive models

2026-07-23 · Nicolás Carrizosa, Vanesa Guerrero, María Durbán arxiv

B-spline regression constitutes a widely used framework for nonparametric modeling. The performance of this methodology depends on specifying the number and placement of changepoints, known as knots, prior to the estimat…

UTA-poly and UTA-splines: additive value functions with polynomial marginals

2016-03-05 · Olivier Sobrie, Nicolas Gillis, Vincent Mousseau, Marc Pirlot

Additive utility function models are widely used in multiple criteria decision analysis. In such models, a numerical value is associated to each alternative involved in the decision problem. It is computed by aggregating…

Kernel Meets Sieve: Post-Regularization Confidence Bands for Sparse Additive Model

2015-03-10 · Junwei Lu, Mladen Kolar, Han Liu

We develop a novel procedure for constructing confidence bands for components of a sparse additive model. Our procedure is based on a new kernel-sieve hybrid estimator that combines two most popular nonparametric estimat…

Additive models