Full Bayesian Significance Testing for Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zehua, Li, Zimeng, Wang, Jingyuan, He, Yue
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909081608912896
author Liu, Zehua
Li, Zimeng
Wang, Jingyuan
He, Yue
author_facet Liu, Zehua
Li, Zimeng
Wang, Jingyuan
He, Yue
contents Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called \textit{n}FBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, \textit{n}FBST can test not only global significance but also local and instance-wise significance, which previous testing methods don't focus on. Moreover, \textit{n}FBST is a general framework that can be extended based on the measures selected, such as Grad-\textit{n}FBST, LRP-\textit{n}FBST, DeepLIFT-\textit{n}FBST, LIME-\textit{n}FBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13335
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Full Bayesian Significance Testing for Neural Networks
Liu, Zehua
Li, Zimeng
Wang, Jingyuan
He, Yue
Machine Learning
Artificial Intelligence
Significance testing aims to determine whether a proposition about the population distribution is the truth or not given observations. However, traditional significance testing often needs to derive the distribution of the testing statistic, failing to deal with complex nonlinear relationships. In this paper, we propose to conduct Full Bayesian Significance Testing for neural networks, called \textit{n}FBST, to overcome the limitation in relationship characterization of traditional approaches. A Bayesian neural network is utilized to fit the nonlinear and multi-dimensional relationships with small errors and avoid hard theoretical derivation by computing the evidence value. Besides, \textit{n}FBST can test not only global significance but also local and instance-wise significance, which previous testing methods don't focus on. Moreover, \textit{n}FBST is a general framework that can be extended based on the measures selected, such as Grad-\textit{n}FBST, LRP-\textit{n}FBST, DeepLIFT-\textit{n}FBST, LIME-\textit{n}FBST. A range of experiments on both simulated and real data are conducted to show the advantages of our method.
title Full Bayesian Significance Testing for Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.13335