The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks
Open accessAbstract
We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope-based slope recovery term is added in the loss function, which further accelerates convergence, thereby reducing the training cost. On the theoretical side, we prove that in the proposed method, the gradient descent algorithms are not attracted to sub-optimal critical points or local minima under practical conditions on the initialization and learning rate, and that the gradient dynamics of the proposed method is not achievable by base methods with any (adaptive) learning rates. We further show that the adaptive activation methods accelerate the convergence by implicitly multiplying conditioning matrices to the gradient of the base method without any explicit computation of the conditioning matrix and the matrix–vector product. The different adaptive activation functions are shown to induce different implicit conditioning matrices. Furthermore, the proposed methods with the slope recovery are shown to accelerate the training process.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
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
(2014) · Cited by 33,419
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-citationIdentity 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
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“Introduction In the recent years, research on neural networks (NNs) has intensified around the world due to their successful applications in many diverse fields such as speech recognition [1], computer vision [2] and natural language translation [3].”
BackgroundJagtap, A. D., Kharazmi, E., & Karniadakis, G. E. (2020) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2020.113028 · Cited by 1,208
Self-citationAdaptive activation functions accelerate convergence in deep and physics-informed neural networks
Jagtap, A. D., Kawaguchi, K., & Karniadakis, G. E. (2020) · Journal of Computational Physics · doi:10.1016/j.jcp.2019.109136 · Cited by 1,127
Self-citationAutomatic differentiation in machine learning: a survey
Baydin, A. G., Pearlmutter, B. A., Radul, A., & Siskind, J. M. (2015) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2019.25 · Cited by 823
Cited by
Physics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718
Self-citationPhysics-Informed Neural Networks for Heat Transfer Problems
Cai, S., Wang, Z., Wang, S., Perdikaris, P., & Karniadakis, G. E. (2021) · Journal of Heat Transfer · doi:10.1115/1.4050542 · Cited by 1,312
Jin, X., Cai, S., Li, H., & Karniadakis, G. E. (2021) · Journal of Computational Physics · doi:10.1016/j.jcp.2020.109951 · Cited by 1,210
Physics‐Informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
Rasht‐Behesht, M., Huber, C., Shukla, K., & Karniadakis, G. E. (2022) · Journal of Geophysical Research: Solid Earth · doi:10.1029/2021jb023120 · Cited by 461
Parallel physics-informed neural networks via domain decomposition
Shukla, K., Jagtap, A. D., & Karniadakis, G. E. (2021) · Journal of Computational Physics · doi:10.1016/j.jcp.2021.110683 · Cited by 431
Self-citation
Metadata
- Authors
- Jagtap, A. D., Kawaguchi, K., & Em Karniadakis, G.
- Venue
- Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Publisher
- The Royal Society
- Published
- 2020-07
- Volume
- 476
- Issue
- 2239
- Pages
- 20200334
- ISSN
- 1364-5021 (ISSN-L)
- 1471-2946
- OpenAlex
- W2975003945
- Cited by
- 259
- References
- 16
- FWCI
- 9.38
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks. https://app.cochat.ai/papers/10.1098/rspa.2020.0334
- The paper
- Jagtap, A. D., Kawaguchi, K., & Em Karniadakis, G. (2020). Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences. https://doi.org/10.1098/rspa.2020.0334
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.