Saved in:
Bibliographic Details
Main Author: Chen, Andrew Siyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.18397
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916360611692544
author Chen, Andrew Siyuan
author_facet Chen, Andrew Siyuan
contents In this paper, we introduce a probabilistic extension to Kolmogorov Arnold Networks (KANs) by incorporating Gaussian Process (GP) as non-linear neurons, which we refer to as GP-KAN. A fully analytical approach to handling the output distribution of one GP as an input to another GP is achieved by considering the function inner product of a GP function sample with the input distribution. These GP neurons exhibit robust non-linear modelling capabilities while using few parameters and can be easily and fully integrated in a feed-forward network structure. They provide inherent uncertainty estimates to the model prediction and can be trained directly on the log-likelihood objective function, without needing variational lower bounds or approximations. In the context of MNIST classification, a model based on GP-KAN of 80 thousand parameters achieved 98.5% prediction accuracy, compared to current state-of-the-art models with 1.5 million parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18397
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian Process Kolmogorov-Arnold Networks
Chen, Andrew Siyuan
Machine Learning
In this paper, we introduce a probabilistic extension to Kolmogorov Arnold Networks (KANs) by incorporating Gaussian Process (GP) as non-linear neurons, which we refer to as GP-KAN. A fully analytical approach to handling the output distribution of one GP as an input to another GP is achieved by considering the function inner product of a GP function sample with the input distribution. These GP neurons exhibit robust non-linear modelling capabilities while using few parameters and can be easily and fully integrated in a feed-forward network structure. They provide inherent uncertainty estimates to the model prediction and can be trained directly on the log-likelihood objective function, without needing variational lower bounds or approximations. In the context of MNIST classification, a model based on GP-KAN of 80 thousand parameters achieved 98.5% prediction accuracy, compared to current state-of-the-art models with 1.5 million parameters.
title Gaussian Process Kolmogorov-Arnold Networks
topic Machine Learning
url https://arxiv.org/abs/2407.18397