The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Dying ReLU and Initialization: Theory and Numerical Examples
Open accessAbstract
The dying ReLU refers to the problem when ReLU neurons become inactive and only output 0 for any input. There are many empirical and heuristic explanations of why ReLU neurons die. However, little is known about its theoretical analysis. In this paper, we rigorously prove that a deep ReLU network will eventually die in probability as the depth goes to infinite. Several methods have been proposed to alleviate the dying ReLU. Perhaps, one of the simplest treatments is to modify the initialization procedure. One common way of initializing weights and biases uses symmetric probability distributions, which suffers from the dying ReLU. We thus propose a new initialization procedure, namely, a randomized asymmetric initialization. We show that the new initialization can effectively prevent the dying ReLU. All parameters required for the new initialization are theoretically designed. Numerical examples are provided to demonstrate the effectiveness of the new initialization procedure.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513 · cited 8×
“Hence, we only examine BN, WN and SELU.”
BackgroundInfluentialWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · cited 2×
“However, the performance of other activation functions varies on different tasks and data sets (Ramachandran et al., 2017) and it typically requires a parameter to be turned.”
BackgroundSelf-Normalizing Neural Networks
Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.02515 · Cited by 2,267
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017) · International Journal of Automation and Computing · doi:10.1007/s11633-017-1054-2 · Cited by 559
Cited by
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators
Lu, L., Jin, P., Pang, G., Zhang, Z., & Karniadakis, G. E. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00302-5 · Cited by 3,418
Self-citationLu, L., Meng, X., Cai, S., Mao, Z., Goswami, S., Zhang, Z., & Karniadakis, G. E. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.114778 · Cited by 514
Self-citationLoss of plasticity in deep continual learning
Dohare, S., Hernandez-Garcia, J. F., Lan, Q., Rahman, P., Mahmood, A. R., & Sutton, R. S. (2024) · Nature · doi:10.1038/s41586-024-07711-7 · Cited by 172
Handling Vanishing Gradient Problem Using Artificial Derivative
Hu, Z., Zhang, J., & Ge, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3054915 · Cited by 109
Metadata
- Authors
- Lu, L., Shin, Y., Su, Y., & Em Karniadakis, G.
- Venue
- Communications in Computational Physics
- Publisher
- Global Science Press
- Published
- 2020-06
- Volume
- 28
- Issue
- 5
- Pages
- 1671-1706
- ISSN
- 1815-2406 (ISSN-L)
- 1991-7120
- OpenAlex
- W2922301133
- Cited by
- 281
- References
- 9
- FWCI
- 11.55
- 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: Dying ReLU and Initialization: Theory and Numerical Examples. https://app.cochat.ai/papers/10.4208/cicp.oa-2020-0165
- The paper
- Lu, L., Shin, Y., Su, Y., & Em Karniadakis, G. (2020). Dying ReLU and Initialization: Theory and Numerical Examples. Communications in Computational Physics. https://doi.org/10.4208/cicp.oa-2020-0165
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.