Revisiting squared-error and cross-entropy functions for training neural network classifiers
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Cross-entropy error is better than squared error in classification and detection problems.
“The cross-entropy error is shown to be better than the squared error in classification and detection problems [47].”
From Deep learning-enabled anomaly detection for IoT systems (2023) · cites this paper as [47]
Cites
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
An integrated decision support system based on ANN and Fuzzy_AHP for heart failure risk prediction
Samuel, O. W., Asogbon, G. M., Sangaiah, A. K., Fang, P., & Li, G. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.10.020 · Cited by 425 · see citing works
Deep learning-enabled anomaly detection for IoT systems
Abusitta, A., de Carvalho, G. H. S., Wahab, O. A., Halabi, T., Fung, B. C. M., & Mamoori, S. A. (2023) · Internet of Things · doi:10.1016/j.iot.2022.100656 · Cited by 184 · see citing works
- Authors
- Kline, D. M., & Berardi, V. L.
- Affiliations
- University of North Carolina Wilmington (US)
- Kent State University (US)
- Corresponding author
- Berardi, Victor L.
- Venue
- Neural Computing and Applications
- Published
- 2005-07-14
- Volume
- 14
- Issue
- 4
- Pages
- 310-318
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W2006626130
- Cited by
- 237
- References
- 1
- Citations by year
- 2026: 5 · 2025: 17 · 2024: 20 · 2023: 22 · 2022: 25 · 2021: 34 · 2020: 25 · 2019: 23 · 2018: 17 · 2017: 10 · 2016: 13 · 2015: 5 · 2014: 2 · 2013: 9 · 2012: 3
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Neural Computing and Applications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- cross-entropy loss, squared error loss, neural network training, feedforward neural networks, posterior probability estimation, classification, loss function comparison
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
