A fragmented neural network ensemble method and its application to image classification

Author:

Zhang Xu,Liu ShuaiORCID,Wang Xueli,Li Yumei

Abstract

AbstractIn recent years, deep neural networks have evolved rapidly in engineering technology, with models becoming larger and deeper. However, for most companies, developing large models is extremely costly and highly risky. Researchers usually focus on the performance of the model, neglecting its cost and accessibility. In fact, most regular business scenarios do not require high-level AI. A simple and inexpensive modeling method for fulfilling certain demands for practical applications of AI is needed. In this paper, a Fragmented neural network method is proposed. Inspired by the random forest algorithm, both the samples and features are randomly sampled on image data. Images are randomly split into smaller pieces. Weak neural networks are trained using these fragmented images, and many weak neural networks are then ensembled to build a strong neural network by voting. In this way, sufficient accuracy is achieved while reducing the complexity and data volume of each base learner, enabling mass production through parallel and distributed computing. By conducting experiments on the MNIST and CIFAR10 datasets, we build a model pool using FNN, CNN, DenseNet, and ResNet as the basic network structure. We find that the accuracy of the ensemble weak network is significantly higher than that of each base learner. Meanwhile, the accuracy of the ensemble network is highly dependent on the performance of each base learner. The accuracy of the ensemble network is comparable to or even exceeds that of the full model and has better robustness. Unlike other similar studies, we do not pursue SOTA models. Instead, we achieved results close to the full model with a smaller number of parameters and amount of data.

Funder

Research Foundation for Youth Scholars of Beijing Technology and Business University

Publisher

Springer Science and Business Media LLC

Reference25 articles.

1. Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 779–788. https://doi.org/10.1109/CVPR.2016.91 (IEEE, 2016).

2. Goodfellow, I. et al. Generative adversarial networks. Commun. ACM 63(11), 139–144. https://doi.org/10.1145/3422622 (2020).

3. Devlin, J., Chang, M.W., Lee, K. & Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In Conference of the North-American-Chapter of the Association-for-Computational-Linguistics - Human Language Technologies (NAACL-HLT), Minneapolis, USA (2019).

4. Brown, T.B., Mann, B., Ryder, N. et al. Language Models are Few-Shot Learners. arXiv preprint https://www.arxiv.org/abs/2005.14165v4 (2020).

5. Rokach, L. Ensemble methods for classifiers. In Data Mining and Knowledge Discovery Handbook (Maimon, O., Rokach, L. eds.). 957–980 https://doi.org/10.1007/0-387-25465-X_45 (Springer, 2005).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3