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
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 50 条
  • [1] Extrapolative Bayesian Optimization with Gaussian Process and Neural Network Ensemble Surrogate Models
    Lim, Yee-Fun
    Ng, Chee Koon
    Vaitesswar, U. S.
    Hippalgaonkar, Kedar
    ADVANCED INTELLIGENT SYSTEMS, 2021, 3 (11)
  • [2] Optimisation of manufacturing process parameters using deep neural networks as surrogate models
    Pfrommer, Julius
    Zimmerling, Clemens
    Liu, Jinzhao
    Kaerger, Luise
    Henning, Frank
    Beyerer, Juergen
    51ST CIRP CONFERENCE ON MANUFACTURING SYSTEMS, 2018, 72 : 426 - 431
  • [3] Gaussian Process Surrogate Models for the CMA Evolution Strategy
    Bajer, Lukas
    Pitra, Zbynek
    Repicky, Jakub
    Holena, Martin
    EVOLUTIONARY COMPUTATION, 2019, 27 (04) : 665 - 697
  • [4] Gaussian Process Neural Additive Models
    Zhang, Wei
    Barr, Brian
    Paisley, John
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 15, 2024, : 16865 - 16872
  • [5] Process synthesis of biodiesel production plant using artificial neural networks as the surrogate models
    Fahmi, Ismail
    Cremaschi, Selen
    COMPUTERS & CHEMICAL ENGINEERING, 2012, 46 : 105 - 123
  • [6] Surrogate Models Assisted by Neural Networks to Assess the Resilience of Networks
    Araujo, Danilo R. B.
    de Barros, Gustavo H. P. S.
    Bastos-Filho, Carmelo J. A.
    Martins-Filho, Joaquim F.
    2017 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2017,
  • [7] Iterative construction of Gaussian process surrogate models for Bayesian inference
    Alawieh, Leen
    Goodman, Jonathan
    Bell, John B.
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2020, 207 : 55 - 72
  • [8] Estimating Regions of Wireless Coexistence with Gaussian Process Surrogate Models
    Rezac, Jacob D.
    Hess, Noel C.
    Coder, Jason B.
    2021 JOINT IEEE INTERNATIONAL SYMPOSIUM ON ELECTROMAGNETIC COMPATIBILITY, SIGNAL & POWER INTEGRITY, AND EMC EUROPE (EMC+SIPI AND EMC EUROPE), 2021, : 722 - 727
  • [9] Implementing Gaussian process inference with neural networks
    Frean, Marcus
    Lilley, Matt
    Boyle, Phillip
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2006, 16 (05) : 321 - 327
  • [10] Gaussian Process Neural Networks for Speech Recognition
    Lam, Max W. Y.
    Hu, Shoukang
    Xie, Xurong
    Liu, Shansong
    Yu, Jianwei
    Su, Rongfeng
    Liu, Xunying
    Meng, Helen
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1778 - 1782