The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Improving deep neural networks using softplus units
Abstract
Recently, DNNs have achieved great improvement for acoustic modeling in speech recognition tasks. However, it is difficult to train the models well when the depth grows. One main reason is that when training DNNs with traditional sigmoid units, the derivatives damp sharply while back-propagating between layers, which restrict the depth of model especially with insufficient training data. To deal with this problem, some unbounded activation functions have been proposed to preserve sufficient gradients, including ReLU and softplus. Compared with ReLU, the smoothing and nonzero properties of the in gradient makes softplus-based DNNs perform better in both stabilization and performance. However, softplus-based DNNs have been rarely exploited for the phoneme recognition task. In this paper, we explore the use of softplus units for DNNs in acoustic modeling for context-independent phoneme recognition tasks. The revised RBM pre-training and dropout strategy are also applied to improve the performance of softplus units. Experiments show that, the DNNs with softplus units get significantly performance improvement and uses less epochs to get convergence compared to the DNNs trained with standard sigmoid units and ReLUs.
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
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Cited by
Activation Functions: Comparison of trends in Practice and Research for Deep Learning
Nwankpa, C. E., Ijomah, W., Gachagan, A., & Marshall, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03378 · Cited by 1,240
Activation 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
Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification
Wan, S., Gong, C., Zhong, P., Du, B., Zhang, L., & Yang, J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2949180 · Cited by 553
Deep learning in robotics: A review of recent research
Pierson, H. A., & Gashler, M. S. (2017) · Advanced Robotics · doi:10.1080/01691864.2017.1365009 · Cited by 331
Multikernel Capsule Network for Schizophrenia Identification
Wang, T., Bezerianos, A., Cichocki, A., & Li, J. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3035282 · Cited by 63
Malinverni, D., Zamuner, S., Rebeaud, M. E., Barducci, A., Nillegoda, N. B., & De Los Rios, P. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218217120 · Cited by 39
Evaluation of Missing Data Imputation Methods for an Enhanced Distributed PV Generation Prediction
Sundararajan, A., & Sarwat, A. I. (2020) · Advances in Intelligent Systems and Computing · doi:10.1007/978-3-030-32520-6_43 · Cited by 22
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Ren, L., Liu, Y., Lu, Y., Shen, Y., Liang, C., & Chen, W. (2024) · arXiv · doi:10.48550/arxiv.2406.07522 · Cited by 8
“The selective gate is then calculated through a low-rank projection followed by Softplus (Zheng et al., 2015), where W r ∈ R d e × d r , W q ∈ R d r × d e and d r is the low-rank dimension. b ∈ R d e is carefully initialized so that ∆ ∈ [∆ min , ∆ max ] after the initialization stage.”
Metadata
- Authors
- Zheng, H., Yang, Z., Liu, W., Liang, J., & Li, Y.
- Venue
- 2015 International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Published
- 2015-07
- Pages
- 1-4
- OpenAlex
- W1667249920
- Cited by
- 221
- References
- 2
- FWCI
- 2.08
- 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.