Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification
Open accessThe DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.
Abstract
Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its "automatic" characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 3×
“Among the existing theoretical evidence, skip connections defying the VG problems receive the most recognition [35], [36].”
BackgroundMethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“learning [1], have shown remarkable superiority in various real-world applications over most machine learning approaches [2], [3], [4], [5]. Sincetheyearof1998whenthefirstversionoftheCNN(i.e., LeNet5 [6]) was proposed, diverse CNN variants have been developed, such as AlexNet [2], VGG [7], GoogleNet [8], ResNet [9] and…”
MethodA fast and elitist multiobjective genetic algorithm: NSGA-II
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.996017 · Cited by 50,053 · cited 1×
“Based on our previous work [58], the tournament selection with or without replacement almost has no different bias to the final performance, and the replacement mechanism used in the proposed algorithm is just to follow the common practice [27], [28], [30].”
MethodDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
(2014) · Cited by 33,419
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
No free lunch theorems for optimization
Wolpert, D. H., & Macready, W. G. (1997) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.585893 · Cited by 14,237 · cited 1×
“Based on the “No Free Lunch Theorems [66],” we should realize that CNNs whose architectures are designed with manual tuning should have better classification accuracy than the automatic ones including the proposed algorithm.”
MethodTensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
(2017) · Cited by 11,625
Genetic Algorithms + Data Structures = Evolution Programs
Michalewicz, Z. (1992) · Artificial Intelligence · doi:10.1007/978-3-662-02830-8 · Cited by 11,553
An Introduction to Genetic Algorithms
Mitchell, M. (1996) · doi:10.7551/mitpress/3927.001.0001 · Cited by 11,340
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 7,831
Handbook of Genetic Algorithms
Davis, L. D. (1991) · Cumulative Index of Computer Aided Architectural Design · Cited by 7,330
(2011) · Cited by 6,993
Bäck, T. (1996) · Oxford University Press eBooks · doi:10.1093/oso/9780195099713.001.0001 · Cited by 5,113
Genetic Algorithms + Data Structures = Evolution Programs
Michalewicz, Z. (1996) · Springer eBooks · doi:10.1007/978-3-662-03315-9 · Cited by 5,095
Learning to forget: Continual prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 4,823
Haupt, R. L., & Haupt, S. E. (2003) · Wiley eBooks · doi:10.1002/0471671746 · Cited by 4,246
Neural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
DARTS: Differentiable architecture search
Liu, H., Simonyan, K., & Yang, Y. (2018) · arXiv · doi:10.48550/arxiv.1806.09055 · Cited by 3,248
Genetic Algorithms and Machine Learning
Goldberg, D. E., & Holland, J. H. (1988) · Machine Learning · doi:10.1023/a:1022602019183 · Cited by 3,193 · cited 1×
“In principle, only selecting the top | P t | best individuals for the next generation easily causes the premature phenomenon [52], which will lead the algorithm trap into a local optimum [23], [53].”
BackgroundImproved regularization of convolutional neural networks with cutout
DeVries, T., & Taylor, G. W. (2017) · arXiv · doi:10.48550/arxiv.1708.04552 · Cited by 2,776
Hawkins, D. M. (2004) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci0342472 · Cited by 2,522 · cited 1×
“However, the fully connected layer easily results in the overfitting phenomenon [40] due to its dense connection [41].”
BackgroundLearning to forget: continual prediction with LSTM
Gers, F. A. (1999) · 9th International Conference on Artificial Neural Networks: ICANN '99 · doi:10.1049/cp:19991218 · Cited by 2,337
Srinivas, M., & Patnaik, L. M. (1994) · Computer · doi:10.1109/2.294849 · Cited by 2,180
Stochastic Gradient Descent Tricks
Bottou, L. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_25 · Cited by 1,929
A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II
Deb, K. (2002) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.6487416 · Cited by 1,554
(1998) · Choice Reviews Online · doi:10.5860/choice.35-5711 · Cited by 1,408
Pattern Recognition and Machine Learning
Maindonald, J. (2007) · Journal of Statistical Software · doi:10.18637/jss.v017.b05 · Cited by 1,349
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.06228 · Cited by 1,246
An introduction to genetic algorithms
Deb, K. (1999) · Sadhana · doi:10.1007/bf02823145 · Cited by 1,176
Deep convolutional neural networks for LVCSR
Sainath, T. N., Mohamed, A.-R., Kingsbury, B., & Ramabhadran, B. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639347 · Cited by 1,053
Genetic Programming: An Introduction
Banzhaf, W., Keller, R. E., & Nordin, P. C. (1997) · Cited by 1,052
Pattern recognition and machine learning
(1993) · Choice Reviews Online · doi:10.5860/choice.30-3308 · Cited by 1,046
Genetic Algorithms, Tournament Selection, and the Effects of Noise.
Miller, B. L., & Goldberg, D. E. (1995) · Cited by 962
(2014) · arXiv (Cornell University) · Cited by 942
Miller, J. F., & Thomson, P. (2000) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-46239-2_9 · Cited by 914
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv · doi:10.48550/arxiv.1505.00387 · Cited by 912
Banzhaf, W., Fogarty, T. C., Schoenauer, M., & Poli, R. (1998) · Lecture notes in computer science · doi:10.1007/bfb0055923 · Cited by 825
Evolving Deep Convolutional Neural Networks for Image Classification
Sun, Y., Xue, B., Zhang, M., & Yen, G. G. (2020) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2916183 · Cited by 775
Self-citationXie, L., & Yuille, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.154 · Cited by 740
The Box Plot: A Simple Visual Method to Interpret Data
Williamson, D. F., Parker, R. A., & Kendrick, J. S. (1989) · Annals of Internal Medicine · doi:10.7326/0003-4819-110-11-916 · Cited by 702
THE EVOLUTIONARY STRATEGY OF THE EQUIDAE AND THE ORIGINS OF RUMEN AND CECAL DIGESTION
Janis, C. (1976) · Evolution · doi:10.1111/j.1558-5646.1976.tb00957.x · Cited by 593
Efficient Architecture Search by Network Transformation
Cai, H., Chen, T., Zhang, W., Yu, Y., & Wang, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11709 · Cited by 557
IGD Indicator-Based Evolutionary Algorithm for Many-Objective Optimization Problems
Sun, Y., Yen, G. G., & Yi, Z. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2018.2791283 · Cited by 519
Self-citationSchmitt, L. M. (2001) · Theoretical Computer Science · doi:10.1016/s0304-3975(00)00406-0 · Cited by 512
A genetic programming approach to designing convolutional neural network architectures
Suganuma, M., Shirakawa, S., & Nagao, T. (2017) · Proceedings of the Genetic and Evolutionary Computation Conference · doi:10.1145/3071178.3071229 · Cited by 491
Large-Scale Evolution of Image Classifiers
Real, E., Moore, S., Selle, A. P., Saxena, S., Suematsu, Y. I. L., Tan, J., Le, Q. V., & Kurakin, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01041 · Cited by 466
Transfer Learning-Based Dynamic Multiobjective Optimization Algorithms
Jiang, M., Huang, Z., Qiu, L., Huang, W., & Yen, G. G. (2018) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2017.2771451 · Cited by 419
Self-citationXie, L., & Yuille, A. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · Cited by 377
Designing Neural Network Architectures using Reinforcement Learning
Baker, B., Gupta, O., Naik, N., & Raskar, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02167 · Cited by 372
Skip Connections Eliminate SingularitiesPreprint
Orhan, A. E., & Pitkow, X. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.09175 · Cited by 249
(2017) · Interval Analysis · doi:10.1515/9783110499469-009 · Cited by 235
GENETIC ALGORITHM WITH ELITIST MODEL AND ITS CONVERGENCE
BHANDARI, D., MURTHY, C. A., & PAL, S. K. (1996) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001496000438 · Cited by 224
Nag, K., & Pal, N. R. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2404806 · Cited by 193
Training Deep Convolutional Neural Networks to Play Go
Clark, C., & Storkey, A. (2015) · Cited by 131
Parallel preconditioned conjugate gradient algorithm on GPU
Helfenstein, R., & Koko, J. (2011) · Journal of Computational and Applied Mathematics · doi:10.1016/j.cam.2011.04.025 · Cited by 129
A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
Suganuma, M., Shirakawa, S., & Nagao, T. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/755 · Cited by 115
Practical Network Blocks Design with Q-Learning.Preprint
Zhong, Z., Yan, J., & Liu, C. (2017) · arXiv (Cornell University) · Cited by 99
Ahn, C. W. (2006) · Springer eBooks · doi:10.1007/11543138_2 · Cited by 53
Improved Regularity Model-Based EDA for Many-Objective Optimization
Sun, Y., Yen, G. G., & Yi, Z. (2018) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2018.2794319 · Cited by 39
Self-citationA novel genetic algorithm and its application to digital filter design
Zhang, G., Gu, Y., Hu, L., et al. (2004) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2003.1252754 · Cited by 29
Reference line-based Estimation of Distribution Algorithm for many-objective optimization
Sun, Y., Yen, G. G., & Zhang, Y. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.06.021 · Cited by 26
Self-citation
Cited by
Genetic algorithms: theory, genetic operators, solutions, and applications
Alhijawi, B., & Awajan, A. (2024) · Evolutionary Intelligence · doi:10.1007/s12065-023-00822-6 · Cited by 723
A Survey on Evolutionary Neural Architecture Search
Liu, Y., Sun, Y., Xue, B., Zhang, M., Yen, G. G., & Tan, K. C. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3100554 · Cited by 644
Self-citationThe Colony Predation Algorithm
Tu, J., Chen, H., Wang, M., & Gandomi, A. H. (2021) · Journal of Bionic Engineering · doi:10.1007/s42235-021-0050-y · Cited by 571
Evolutionary Transfer Optimization - A New Frontier in Evolutionary Computation Research
Tan, K. C., Feng, L., & Jiang, M. (2021) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.3039066 · Cited by 315
Chen, M., Yu, L., Zhi, C., Sun, R., Zhu, S., Gao, Z., Ke, Z., Zhu, M., & Zhang, Y. (2022) · Computers in Industry · doi:10.1016/j.compind.2021.103551 · Cited by 295
Metadata
- Authors
- Sun, Y., Xue, B., Zhang, M., Yen, G. G., & Lv, J.
- Venue
- IEEE Transactions on Cybernetics
- Published
- 2020-09
- Volume
- 50
- Issue
- 9
- Pages
- 3840-3854
- ISSN
- 2168-2267 (ISSN-L)
- 2168-2275
- OpenAlex
- W2887063112
- Cited by
- 870
- References
- 77
- FWCI
- 53.83
- Type
- journal article
- 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
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.