The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
A Review of Activation Function for Artificial Neural Network
Abstract
The activation function plays an important role in the training and the performance of an Artificial Neural Network. They provide the necessary non-linear properties to any Artificial Neural Network. In this work, we provide a review of the most common and recent activation functions used in the hidden layer of an artificial Neural Network.
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
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
(2011) · Cited by 6,993
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 7×
“Exponential Linear Unit ELU was first proposed in [7] as an improvement over ReLU.”
BackgroundMethodResultInfluentialOn the approximate realization of continuous mappings by neural networks
Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206 · cited 2×
“Various work have been done into using sigmoid in artificial neural networks [14] [4] [2] [15].”
BackgroundConvergence Results for Neural Networks via Electrodynamics
Panigrahy, R., Rahimi, A., Sachdeva, S., & Zhang, Q. (2018) · Leibniz international proceedings in informatics · doi:10.4230/lipics.itcs.2018.22 · Cited by 2,761
Deep Learning using Rectified Linear Units (ReLU)
Agarap, A. F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08375 · Cited by 2,399
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×
“M ETHODOLOGY OF COMPARISON In this work we consider eight major activation functions, two of which are “novel” and proposed in [10] and in [11].”
BackgroundMethodSelf-Normalizing Neural Networks
Klambauer, G., Unterthiner, T., Mayr, A., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.02515 · Cited by 2,267
Mish: A Self Regularized Non-Monotonic Neural Activation FunctionPreprint
Misra, D. (2019) · arXiv (Cornell University) · Cited by 678
Parametric Exponential Linear Unit for Deep Convolutional Neural Networks
Trottier, L., Giguere, P., & Chaib-draa, B. (2017) · 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA) · doi:10.1109/icmla.2017.00038 · Cited by 200
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practicePreprint
Pennington, J., Schoenholz, S. S., & Ganguli, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04735 · Cited by 180
Approximation by ridge functions and neural networks with one hidden layer
Chui, C. K., & Li, X. (1992) · Journal of Approximation Theory · doi:10.1016/0021-9045(92)90081-x · Cited by 179
Deep Residual Networks with Exponential Linear Unit
Shah, A. U., Kadam, E., Shah, H., Shinde, S., & Shingade, S. (2016) · International Symposium on Computer Vision and the Internet (VisionNet) · doi:10.1145/2983402.2983406 · Cited by 140
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacityPreprint
Yun, C., Sra, S., & Jadbabaie, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.07770 · Cited by 125
Improving deep neural network with Multiple Parametric Exponential Linear Units
Li, Y., Fan, C., Li, Y., Wu, Q., & Ming, Y. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.01.084 · Cited by 95
Hidden unit specialization in layered neural networks: ReLU vs. sigmoidal activation
Oostwal, E., Straat, M., & Biehl, M. L. (2020) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2020.125517 · Cited by 85
LiSHT: Non-parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks
Roy, S. K., Manna, S., Dubey, S. R., & Chaudhuri, B. B. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-31407-0_35 · Cited by 81
Weighted sigmoid gate unit for an activation function of deep neural network
Tanaka, M. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.05.017 · Cited by 74
SNDCNN: Self-Normalizing Deep CNNs with Scaled Exponential Linear Units for Speech Recognition
Huang, Z., Ng, T., Liu, L., Mason, H., Zhuang, X., & Liu, D. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053973 · Cited by 57
How degenerate is the parametrization of neural networks with the ReLU activation function?Preprint
Berner, J., Elbrächter, D., & Grohs, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.09803 · Cited by 44
Why RELU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks
Douglas, S. C., & Yu, J. (2018) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2018.8645556 · Cited by 42
The Benefits of Over-parameterization at Initialization in Deep ReLU NetworksPreprint
Arpit, D., & Bengio, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.03611 · Cited by 35
An ELU Network with Total Variation for Image Denoising
Wang, T., Qin, Z., & Zhu, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70090-8_24 · Cited by 26
Mean Field Theory of Activation Functions in Deep Neural NetworksPreprint
Milletarí, M., Chotibut, T., & Trevisanutto, P. E. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08786 · Cited by 9
Cited by
Faroughi, S. A., Pawar, N. M., Fernandes, C., Raissi, M., Das, S., Kalantari, N. K., & Kourosh Mahjour, S. (2024) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4064449 · Cited by 257
Tran, K., Vu, H.-C., Pham, L., Boudaoud, N., & Nguyen, H.-S.-H. (2024) · Mathematics · doi:10.3390/math12101569 · Cited by 14
“The three AB-LSTM blocks’ outputs are concatenated and passed to a linear layer with a Sigmoid activation function, ensuring a final output range of (0,1) [48].”
Metadata
- Authors
- Rasamoelina, A. D., Adjailia, F., & Sincak, P.
- Venue
- 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI)
- Publisher
- IEEE
- Published
- 2020-01
- Pages
- 281-286
- OpenAlex
- W3034021666
- Cited by
- 319
- References
- 25
- FWCI
- 10.99
- Type
- conference paper
- Language
- en
- Open access
- closed
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.