The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Optimization of CNN through Novel Training Strategy for Visual Classification Problems
Open accessAbstract
The convolution neural network (CNN) has achieved state-of-the-art performance in many computer vision applications e.g., classification, recognition, detection, etc. However, the global optimization of CNN training is still a problem. Fast classification and training play a key role in the development of the CNN. We hypothesize that the smoother and optimized the training of a CNN goes, the more efficient the end result becomes. Therefore, in this paper, we implement a modified resilient backpropagation (MRPROP) algorithm to improve the convergence and efficiency of CNN training. Particularly, a tolerant band is introduced to avoid network overtraining, which is incorporated with the global best concept for weight updating criteria to allow the training algorithm of the CNN to optimize its weights more swiftly and precisely. For comparison, we present and analyze four different training algorithms for CNN along with MRPROP, i.e., resilient backpropagation (RPROP), Levenberg–Marquardt (LM), conjugate gradient (CG), and gradient descent with momentum (GDM). Experimental results showcase the merit of the proposed approach on a public face and skin dataset.
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
(2010) · Cited by 14,134
Training feedforward networks with the Marquardt algorithm
Hagan, M. T., & Menhaj, M. B. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.329697 · Cited by 7,701
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2603342 · Cited by 6,214
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
Riedmiller, M., & Braun, H. (2002) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1993.298623 · Cited by 3,917
Why Does Unsupervised Pre-training Help Deep Learning?
Erhan, D., Bengio, Y., Courville, A. C., Manzagol, P.-A., Vincent, P., & Samy Bengio, A. (2010) · Journal of Machine Learning Research · Cited by 2,573
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
(2011) · Springer eBooks · doi:10.1007/978-0-85729-932-1 · Cited by 1,819
Example-based learning for view-based human face detection
Sung, K.-K., & Poggio, T. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.655648 · Cited by 1,773
Skin segmentation using color pixel classification: analysis and comparison
Phung, S. L., Bouzerdoum, A., & Chai, D. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.17 · Cited by 743
Robust Face Recognition via Multimodal Deep Face Representation
Ding, C., & Tao, D. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2477042 · Cited by 449
Bulan, O., Kozitsky, V., Ramesh, P., & Shreve, M. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2639020 · Cited by 206
A Pyramidal Neural Network For Visual Pattern Recognition
Phung, S. L., & Bouzerdoum, A. (2007) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.884677 · Cited by 129
Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition
Hu, Q., Wang, H., Li, T., & Shen, C. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2679114 · Cited by 107
Neural Speed Controller Trained Online by Means of Modified RPROP Algorithm
Pajchrowski, T., Zawirski, K., & Nowopolski, K. (2014) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2014.2359620 · Cited by 97
Facial expression recognition with FRR‐CNN
Xie, S., & Hu, H. (2017) · Electronics Letters · doi:10.1049/el.2016.4328 · Cited by 96
Deep Texture Features for Robust Face Spoofing Detection
de Souza, G. B., Santos, D. F. D. S., Pires, R. G., Marana, A. N., & Papa, J. P. (2017) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2017.2764460 · Cited by 65
Face recognition: A novel un-supervised convolutional neural network method
Rehman, S. U., Tu, S., Huang, Y., & Yang, Z. (2016) · IEEE International Conference of Online Analysis and Computing Science (ICOACS) · doi:10.1109/icoacs.2016.7563066 · Cited by 56
Self-citationStacking PCANet +: An Overly Simplified ConvNets Baseline for Face Recognition
Low, C.-Y., Teoh, A. B. J., & Toh, K. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2749763 · Cited by 39
Recognition of handwritten digits using the signature features and Optimum-Path Forest Classifier
Lopes, G. S., da Silva, D. C., Rodrigues, A. W. D. O., & Filho, P. P. R. (2016) · IEEE Latin America Transactions · doi:10.1109/tla.2016.7530445 · Cited by 20
Cited by
(1996) · Institutional Research Information System University of Turin (University of Turin) · doi:10.1111/j · Cited by 5,486
Metadata
- Authors
- Rehman, S., Tu, S., Rehman, O., Huang, Y., Magurawalage, C., & Chang, C.-C.
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2018-04-17
- Volume
- 20
- Issue
- 4
- Pages
- 290
- ISSN
- 1099-4300 (ISSN-L)
- OpenAlex
- W2800732852
- Cited by
- 265
- References
- 19
- FWCI
- 7.48
- Type
- journal article
- Language
- en
- Open access
- gold
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.