The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
Open accessAbstract
We employ adaptive activation functions for regression in deep and physics-informed neural networks (PINNs) to approximate smooth and discontinuous functions as well as solutions of linear and nonlinear partial differential equations. In particular, we solve the nonlinear Klein-Gordon equation, which has smooth solutions, the nonlinear Burgers equation, which can admit high gradient solutions, and the Helmholtz equation. We introduce a scalable hyper-parameter in the activation function, which can be optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The adaptive activation function has better learning capabilities than the traditional one (fixed activation) as it improves greatly the convergence rate, especially at early training, as well as the solution accuracy. To better understand the learning process, we plot the neural network solution in the frequency domain to examine how the network captures successively different frequency bands present in the solution. We consider both forward problems, where the approximate solutions are obtained, as well as inverse problems, where parameters involved in the governing equation are identified. Our simulation results show that the proposed method is a very simple and effective approach to increase the efficiency, robustness and accuracy of the neural network approximation of nonlinear functions as well as solutions of partial differential equations, especially for forward problems. We theoretically prove that in the proposed method, gradient descent algorithms are not attracted to suboptimal critical points or local minima. Furthermore, the proposed adaptive activation functions are shown to accelerate the minimization process of the loss values in standard deep learning benchmarks using CIFAR-10, CIFAR-100, SVHN, MNIST, KMNIST, Fashion-MNIST, and Semeion datasets with and without data augmentation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384
Self-citationBertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 11,726
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Whitham, G. B., & Fowler, R. G. (1975) · Physics Today · doi:10.1063/1.3069011 · Cited by 8,179
An overview of gradient descent optimization algorithms
Ruder, S. (2016) · arXiv · doi:10.48550/arxiv.1609.04747 · Cited by 4,962
Universal approximation bounds for superpositions of a sigmoidal function
Barron, A. R. (1993) · IEEE Transactions on Information Theory · doi:10.1109/18.256500 · Cited by 2,804
A Mathematical Model Illustrating the Theory of Turbulence
Burgers, J. M. (1948) · Advances in Applied Mechanics · doi:10.1016/s0065-2156(08)70100-5 · Cited by 2,573
Weik, M. H. (2000) · Computer Science and Communications Dictionary · doi:10.1007/1-4020-0613-6_12436 · Cited by 2,570
Artificial neural networks for solving ordinary and partial differential equations
Lagaris, I. E., Likas, A., & Fotiadis, D. I. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.712178 · Cited by 2,412
Automatic Differentiation in Machine Learning: a Survey
Baydin, A. G., Pearlmutter, B. A., Radul, A., & Siskind, J. M. (2015) · Maynooth University ePrints and eTheses Archive (Maynooth University) · Cited by 2,029
Solitons and Nonlinear Wave Equations
Dodd, R. K., MORRIS, H. C., Eilbeck, J. C., & Gibbon, J. (1982) · International Linear Collider · Cited by 2,014
On the Spectral Bias of Neural NetworksPreprint
Rahaman, N., Baratin, A., Arpit, D., Draxler, F., Lin, M., Hamprecht, F. A., Bengio, Y., & Courville, A. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.08734 · Cited by 1,915
Partial Differential Equations in Physics
(1949) · Pure and applied mathematics · doi:10.1016/s0079-8169(08)x6048-9 · Cited by 1,575
Data-driven discovery of partial differential equations
Rudy, S. H., Brunton, S. L., Proctor, J. L., & Kutz, J. N. (2017) · Science Advances · doi:10.1126/sciadv.1602614 · Cited by 1,557
Hidden physics models: Machine learning of nonlinear partial differential equations
Raissi, M., & Karniadakis, G. E. (2018) · Journal of Computational Physics · doi:10.1016/j.jcp.2017.11.039 · Cited by 1,349
Self-citationA Closer Look at Memorization in Deep Networks
Arpit, D., Jastrzębski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., Maharaj, T., Fischer, A., Courville, A., Bengio, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1706.05394 · Cited by 1,307
Error bounds for approximations with deep ReLU networks
Yarotsky, D. (2017) · Neural Networks · doi:10.1016/j.neunet.2017.07.002 · Cited by 1,085
Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
Lagaris, I. E., Likas, A., & Fotiadis, D. I. (1998) · Cited by 944
SOME RECENT RESEARCHES ON THE MOTION OF FLUIDS
BATEMAN, H. (1915) · Monthly Weather Review · doi:10.1175/1520-0493(1915)43<163:srrotm>2.0.co;2 · Cited by 648
A paradigm for data-driven predictive modeling using field inversion and machine learning
Parish, E. J., & Duraisamy, K. (2016) · Journal of Computational Physics · doi:10.1016/j.jcp.2015.11.012 · Cited by 620
Machine learning of linear differential equations using Gaussian processes
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2017) · Journal of Computational Physics · doi:10.1016/j.jcp.2017.07.050 · Cited by 584
Self-citationFrequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
John Xu, Z.-Q., Zhang, Y., Luo, T., Xiao, Y., & Ma, Z. (2020) · Communications in Computational Physics · doi:10.4208/cicp.oa-2020-0085 · Cited by 522
Deep learning of vortex-induced vibrations
Raissi, M., Wang, Z., Triantafyllou, M. S., & Karniadakis, G. E. (2019) · Journal of Fluid Mechanics · doi:10.1017/jfm.2018.872 · Cited by 404
Self-citationDeep learning of vortex-induced vibrationsPreprint
Raissi, M., Wang, Z., Triantafyllou, M. S., & Karniadakis, G. E. (2019) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 361
Self-citationInferring solutions of differential equations using noisy multi-fidelity data
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2017) · Journal of Computational Physics · doi:10.1016/j.jcp.2017.01.060 · Cited by 323
Self-citationNumerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2018) · SIAM Journal on Scientific Computing · doi:10.1137/17m1120762 · Cited by 318
Self-citationSpectral and finite difference solutions of the Burgers equation
Basdevant, C., Deville, M., Haldenwang, P., Lacroix, J. M., Ouazzani, J., Peyret, R., Orlandi, P., & Patera, A. T. (1986) · Computers & Fluids · doi:10.1016/0045-7930(86)90036-8 · Cited by 246
Bayesian Numerical Homogenization
Owhadi, H. (2015) · Multiscale Modeling and Simulation · doi:10.1137/140974596 · Cited by 240
Machine Learning Methods for Data-Driven Turbulence Modeling
Zhang, Z. J., & Duraisamy, K. (2015) · AIAA Computational Fluid Dynamics Conference · doi:10.2514/6.2015-2460 · Cited by 217
New Approaches in Turbulence and Transition Modeling Using Data-driven Techniques
Duraisamy, K., Zhang, Z. J., & Singh, A. P. (2015) · 53rd AIAA Aerospace Sciences Meeting · doi:10.2514/6.2015-1284 · Cited by 208
Adaptive activation functions in convolutional neural networks
Qian, S., Liu, H., Liu, C., Wu, S., & Wong, H. S. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.06.070 · Cited by 185
Data-driven discovery of PDEs in complex datasets
Berg, J., & Nyström, K. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2019.01.036 · Cited by 174
A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence ModelingPreprint
Wang, J., Wu, J., Ling, J., Iaccarino, G., & Xiao, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.07102 · Cited by 76
A Robust-Equitable Measure for Feature Ranking and Selection
Ding, A. A., Dy, J., Li, Y., & Chang, Y. (2017) · Journal of Machine Learning Research · Cited by 69
The extreme learning machine learning algorithm with tunable activation function
Li, B., Li, Y., & Rong, X. (2012) · Neural Computing and Applications · doi:10.1007/s00521-012-0858-9 · Cited by 62
On the Spectral Bias of Deep Neural NetworksPreprint
Rahaman, N., Arpit, D., Baratin, A., Draxler, F., Lin, M., Hamprecht, F. A., Bengio, Y., & Courville, A. C. (2018) · arXiv (Cornell University) · Cited by 40
Adaptive Activation Functions for Deep Networks
Dushkoff, M., & Ptucha, R. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.19.coimg-149 · Cited by 32
A New Multi-output Neural Model with Tunable Activation Function and its Applications
Shen, Y., Wang, B., Chen, F., & Cheng, L. (2004) · Neural Processing Letters · doi:10.1007/s11063-004-0637-4 · Cited by 14
Research works printed but not linked: 1
- Caudrey, 1975, The sine-Gordon equation as a model classical field theory, Nuovo Cimento, 25, 497, 10.1007/BF02724733 · doi:10.1007/bf02724733
Cited by
Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next
Cuomo, S., Di Cola, V. S., Giampaolo, F., Rozza, G., Raissi, M., & Piccialli, F. (2022) · Journal of Scientific Computing · doi:10.1007/s10915-022-01939-z · Cited by 2,784
DeepXDE: A Deep Learning Library for Solving Differential Equations
Lu, L., Meng, X., Mao, Z., & Karniadakis, G. E. (2021) · SIAM Review · doi:10.1137/19m1274067 · Cited by 2,512
Self-citationPhysics-informed neural networks (PINNs) for fluid mechanics: a review
Cai, S., Mao, Z., Wang, Z., Yin, M., & Karniadakis, G. E. (2021) · Acta Mechanica Sinica · doi:10.1007/s10409-021-01148-1 · Cited by 2,084
Self-citationPhysics-informed neural networks for high-speed flows
Mao, Z., Jagtap, A. D., & Karniadakis, G. E. (2020) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2019.112789 · Cited by 1,282
Self-citationActivation functions in deep learning: a comprehensive survey and benchmark
Dubey, S. R., Singh, S. K., & Chaudhuri, B. B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.111 · Cited by 1,259
Metadata
- Authors
- Jagtap, A. D., Kawaguchi, K., & Karniadakis, G. E.
- Venue
- Journal of Computational Physics
- Publisher
- Elsevier BV
- Published
- 2020-03
- Volume
- 404
- Pages
- 109136
- ISSN
- 0021-9991 (ISSN-L)
- OpenAlex
- W2948551291
- Cited by
- 1,127
- References
- 43
- FWCI
- 25.44
- Type
- journal article
- Language
- en
- Open access
- bronze
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 314 d)
- Funders
- U.S. Department of Energy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.