Parsimonious neural networks learn interpretable physical laws

被引:19
|
作者
Desai, Saaketh [1 ,2 ]
Strachan, Alejandro [1 ,2 ]
机构
[1] Purdue Univ, Sch Mat Engn, W Lafayette, IN 47907 USA
[2] Purdue Univ, Birck Nanotechnol Ctr, W Lafayette, IN 47907 USA
关键词
D O I
10.1038/s41598-021-92278-w
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Machine learning is playing an increasing role in the physical sciences and significant progress has been made towards embedding domain knowledge into models. Less explored is its use to discover interpretable physical laws from data. We propose parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony. The power and versatility of the approach is demonstrated by developing models for classical mechanics and to predict the melting temperature of materials from fundamental properties. In the first example, the resulting PNNs are easily interpretable as Newton's second law, expressed as a non-trivial time integrator that exhibits time-reversibility and conserves energy, where the parsimony is critical to extract underlying symmetries from the data. In the second case, the PNNs not only find the celebrated Lindemann melting law, but also new relationships that outperform it in the pareto sense of parsimony vs. accuracy.
引用
收藏
页数:9
相关论文
共 50 条
  • [21] Learning to learn by modular neural networks
    Sashima, A
    Hiraki, K
    PROCEEDINGS OF THE TWENTY-SECOND ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, 2000, : 1051 - 1051
  • [22] Econets: Neural networks that learn in an environment
    Parisi, Domenico
    Cecconi, Federico
    Nolfi, Stefan
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1990, 1 (02) : 149 - 168
  • [23] Interpretable logical-probabilistic approximation of neural networks
    Vityaev, Evgenii
    Korolev, Alexey
    COGNITIVE SYSTEMS RESEARCH, 2024, 88
  • [24] Efficient and Interpretable Robot Manipulation With Graph Neural Networks
    Lin, Yixin
    Wang, Austin S.
    Undersander, Eric
    Rai, Akshara
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) : 2740 - 2747
  • [25] Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
    Chen, Siheng
    Eldar, Yonina C.
    Zhao, Lingxiao
    IEEE Transactions on Signal Processing, 2021, 69 : 3699 - 3713
  • [26] Prototype-Based Interpretable Graph Neural Networks
    Ragno, Alessio
    Rosa, Biagio La
    Capobianco, Roberto
    IEEE Transactions on Artificial Intelligence, 2024, 5 (04): : 1486 - 1495
  • [27] Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
    Chen, Siheng
    Eldar, Yonina C.
    Zhao, Lingxiao
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 : 3699 - 3713
  • [28] Interpretable Graph Neural Networks for Heterogeneous Tabular Data
    Alkhatib, Amr
    Bostrom, Henrik
    DISCOVERY SCIENCE, DS 2024, PT I, 2025, 15243 : 310 - 324
  • [29] E pluribus unum interpretable convolutional neural networks
    George Dimas
    Eirini Cholopoulou
    Dimitris K. Iakovidis
    Scientific Reports, 13
  • [30] Unsupervised Keyphrase Extraction via Interpretable Neural Networks
    Joshi, Rishabh
    Balachandran, Vidhisha
    Saldanha, Emily
    Glenski, Maria
    Volkova, Svitlana
    Tsvetkov, Yulia
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1107 - 1119