Gaussian Process Surrogate Models for Neural Networks

被引:0
作者
Li, Michael Y. [1 ]
Grant, Erin [2 ]
Griffiths, Thomas L. [3 ]
机构
[1] Stanford Univ, Dept Comp Sci, Stanford, CA 94305 USA
[2] UCL, Gatsby Computat Neurosci Unit, London, England
[3] Dept Psychol & Comp Sci, Princeton, NJ USA
来源
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE | 2023年 / 216卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Not being able to understand and predict the behavior of deep learning systems makes it hard to decide what architecture and algorithm to use for a given problem. In science and engineering, modeling is a methodology used to understand complex systems whose internal processes are opaque. Modeling replaces a complex system with a simpler, more interpretable surrogate. Drawing inspiration from this, we construct a class of surrogate models for neural networks using Gaussian processes. Rather than deriving kernels for infinite neural networks, we learn kernels empirically from the naturalistic behavior of finite neural networks. We demonstrate our approach captures existing phenomena related to the spectral bias of neural networks, and then show that our surrogate models can be used to solve practical problems such as identifying which points most influence the behavior of specific neural networks and predicting which architectures and algorithms will generalize well for specific datasets.
引用
收藏
页码:1241 / 1252
页数:12
相关论文
共 70 条
  • [41] The Place of Modeling in Cognitive Science
    McClelland, James L.
    [J]. TOPICS IN COGNITIVE SCIENCE, 2009, 1 (01) : 11 - 38
  • [42] Mildenhall B, 2022, COMMUN ACM, V65, P99, DOI 10.1145/3503250
  • [43] Mitchell T, 1980, The need for biases in learning generalizations
  • [44] Murray I., ADV NEURIPS
  • [45] Nair V., 2010, P 27 INT C MACH LEAR, P807
  • [46] Nakkiran P., 2021, PhD thesis
  • [47] Neal R M., 1996, Bayesian learning for neural networks, ppp 29, DOI DOI 10.1007/978-1-4612-0745-02
  • [48] ELEMENTS OF A THEORY OF HUMAN PROBLEM-SOLVING
    NEWELL, A
    SHAW, JC
    SIMON, HA
    [J]. PSYCHOLOGICAL REVIEW, 1958, 65 (03) : 151 - 166
  • [49] Novak R., 2019, P ICLR
  • [50] Rahaman N, 2019, PR MACH LEARN RES, V97