The DOI matches its Crossref record; 44 of the 52 references it cites were found in a registry or an index.
Ensembling neural networks: Many could be better than all
Open accessAbstract
Neural network ensemble is a learning paradigm where many neural networks are jointly used to solve a problem. In this paper, the relationship between the ensemble and its component neural networks is analyzed from the context of both regression and classification, which reveals that it may be better to ensemble many instead of all of the neural networks at hand. This result is interesting because at present, most approaches ensemble all the available neural networks for prediction. Then, in order to show that the appropriate neural networks for composing an ensemble can be effectively selected from a set of available neural networks, an approach named GASEN is presented. GASEN trains a number of neural networks at first. Then it assigns random weights to those networks and employs genetic algorithm to evolve the weights so that they can characterize to some extent the fitness of the neural networks in constituting an ensemble. Finally it selects some neural networks based on the evolved weights to make up the ensemble. A large empirical study shows that, compared with some popular ensemble approaches such as Bagging and Boosting, GASEN can generate neural network ensembles with far smaller sizes but stronger generalization ability. Furthermore, in order to understand the working mechanism of GASEN, the bias-variance decomposition of the error is provided in this paper, which shows that the success of GASEN may lie in that it can significantly reduce the bias as well as the variance.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“Multiple neural networks with identical architectures are trained to form an ensemble , where the predictions of each network in the ensemble are averaged to increase accuracy and generality [24-26].”
From Deep neural network ensembles for THz-TDS refractive index extraction exhibiting resilience to experimental and analytical errors (2023) · cites this paper as [24]
In the citing paper
“It could also be keywords [112], relation triples [154] or even highlighted phrases or sentences [34,78] to plan the content of generated texts.”
From Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2023) · cites this paper as [154]
Citations
Cites
Genetic algorithms in search, optimization, and machine learning
(1989) · Choice Reviews Online · doi:10.5860/choice.27-0936 · Cited by 49,010
An Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1994) · doi:10.1201/9780429246593 · Cited by 40,500
A decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 4×
“The Bagging algorithm [3] employs bootstrap sampling [10] to generate many training sets from the original training set, and then trains a neural network from each of those training sets.”
MethodInfluentialLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Goldberg, D. E., & Shakespeare, W. (2002) · Cited by 16,088
UCI Repository of machine learning databases
Blake, C. L. (1998) · Medical Entomology and Zoology · Cited by 10,582
Wolpert, D. H. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80023-1 · Cited by 7,951
Adaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384 · cited 1×
“Note that there are some approaches using a number of neural networks to accomplish a task in the style of divide-and-conquer [ 23 , 25].”
BackgroundThe Strength of Weak Learnability
Schapire, R. E. (1990) · Machine Learning · doi:10.1007/bf00116037 · Cited by 4,600 · cited 2×
“Boosting is proposed by Schapire [39] and improved by Freund et al. [11, 12].”
Method
Cited by
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
Sagi, O., & Rokach, L. (2018) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1249 · Cited by 3,103
“The GASEN algorithm for example, selects the most suitable inducers in a given ensemble (Zhou et al., 2002).”
BackgroundMethodRokach, L. (2010) · Artificial Intelligence Review · doi:10.1007/s10462-009-9124-7 · Cited by 2,657
“After (Zhou et al. 2002) proved the “many-could-be-better-than-all” theorem, it has become wellknown that it is possible to get a small yet strong ensemble.”
BackgroundMethodDong, X., Yu, Z., Cao, W., Shi, Y., & Ma, Q. (2020) · Frontiers of Computer Science · doi:10.1007/s11704-019-8208-z · Cited by 1,928
“[39] proposed a neural network based ensemble method, where the weights of networks were updated by genetic algorithm.”
MethodBenchmarking state-of-the-art classification algorithms for credit scoring: an update of research
Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015) · European Journal of Operational Research · doi:10.1016/j.ejor.2015.05.030 · Cited by 1,284
“An exemplary approach that uses a more elaborate search method is GASEN (Zhou et al., 2002), which approaches (15) by means of a genetic algorithm.”
Method
Metadata
- Authors
- Zhou, Z.-H., Wu, J., & Tang, W.
- Affiliations
- Nanjing University (CN)
- Corresponding author
- Zhou, Zhi-Hua
- Venue
- Artificial Intelligence
- Publisher
- Elsevier BV
- Published
- 2002-05
- Volume
- 137
- Issue
- 1-2
- Pages
- 239-263
- ISSN
- 0004-3702 (ISSN-L)
- OpenAlex
- W2100128988
- Semantic Scholar
- be4fd29e3225d8451b02683f1a32baef0483266a
- Cited by
- 1,964
- References
- 52
- Citations by year
- 2026: 39 · 2025: 65 · 2024: 69 · 2023: 75 · 2022: 112 · 2021: 152 · 2020: 115 · 2019: 120 · 2018: 119 · 2017: 113 · 2016: 91 · 2015: 111 · 2014: 121 · 2013: 89 · 2012: 81
- FWCI
- 21.03
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (vor, 4131 d)
- Locations
- Artificial Intelligence (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Nanjing University
- 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 › Artificial Intelligence › Machine Learning and ELM
- Keywords
- neural network ensembles, genetic algorithm, ensemble weighting, bias-variance decomposition, regression analysis, classification, model generalization, bagging, boosting
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: Ensembling neural networks: Many could be better than all. https://app.cochat.ai/papers/10.1016/s0004-3702(02)00190-x
- The paper
- Zhou, Z.-H., Wu, J., & Tang, W. (2002). Ensembling neural networks: Many could be better than all. Artificial Intelligence. https://doi.org/10.1016/s0004-3702(02)00190-x
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.