The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Cross-entropy vs. squared error training: a theoretical and experimental comparison
Open accessAbstract
In this paper we investigate the error criteria that are optimized during the training of artificial neural networks (ANN).We compare the bounds of the squared error (SE) and the crossentropy (CE) criteria being the most popular choices in stateof-the art implementations.The evaluation is performed on automatic speech recognition (ASR) and handwriting recognition (HWR) tasks using a hybrid HMM-ANN model.We find that with randomly initialized weights, the squared error based ANN does not converge to a good local optimum.However, with a good initialization by pre-training, the word error rate of our best CE trained system could be reduced from 30.9% to 30.5% on the ASR, and from 22.7% to 21.9% on the HWR task by performing a few additional "fine-tuning" iterations with the SE criterion.
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
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Revisiting squared-error and cross-entropy functions for training neural network classifiers
Kline, D. M., & Berardi, V. L. (2005) · Neural Computing and Applications · doi:10.1007/s00521-005-0467-y · Cited by 237
Cited by
Talebi, H., & Milanfar, P. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2831899 · Cited by 1,023
Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory
Ma, X., Yu, H., Wang, Y., & Wang, Y. (2015) · PLOS ONE · doi:10.1371/journal.pone.0119044 · Cited by 495
Multi-head CNN–RNN for multi-time series anomaly detection: An industrial case study
Canizo, M., Triguero, I., Conde, A., & Onieva, E. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.07.034 · Cited by 420
Kim, D. H., Baddar, W. J., Jang, J., & Ro, Y. M. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2695999 · Cited by 257
Mengu, D., Luo, Y., Rivenson, Y., & Ozcan, A. (2020) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2921376 · Cited by 255
Metadata
- Authors
- Golik, P., Doetsch, P., & Ney, H.
- Venue
- Interspeech 2013
- Publisher
- ISCA
- Published
- 2013-08-25
- Pages
- 1756-1760
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2406273144
- Cited by
- 220
- References
- 2
- FWCI
- 6.07
- Type
- conference paper
- 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: Cross-entropy vs. squared error training: a theoretical and experimental comparison. https://app.cochat.ai/papers/10.21437/interspeech.2013-436
- The paper
- Golik, P., Doetsch, P., & Ney, H. (2013). Cross-entropy vs. squared error training: a theoretical and experimental comparison. Interspeech 2013. https://doi.org/10.21437/interspeech.2013-436
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.