Optimization of Neural Network Architectures for Image Recognition
DOI:
https://doi.org/10.47604/ajcet.2806Keywords:
Optimization, Neural Network Architectures, Image RecognitionAbstract
Purpose: To aim of the study was to analyze the optimization of neural network architectures for image recognition.
Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low cost advantage as compared to a field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries.
Findings: Recent studies on neural network architectures have revealed significant improvements in image recognition by focusing on optimizing network designs. Key findings highlight the effectiveness of using deeper and more complex architectures, such as convolutional neural networks (CNNs) and residual networks (ResNets), which enhance recognition accuracy by capturing intricate features in images. Tuning hyper parameters, such as learning rates, batch sizes, and activation functions, is crucial for optimizing performance. Techniques like dropout, batch normalization, and data augmentation help reduce overfitting and improve the generalization of models.
Unique Contribution to Theory, Practice and Policy: Information bottleneck theory, transfer learning theory & bayesian optimization theory may be used to anchor future studies on optimization of neural network architectures for image recognition. Promote the practical implementation of efficient scaling methods such as Efficient Net across various applications and domains. Advocate for the development of standards and regulations that guide the ethical deployment of AI technologies in image recognition.
Downloads
References
Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. (2016). "Deep variational information bottleneck." arXiv preprint arXiv:1612.00410.
Brown, A., Wang, J., & Maybank, S. (2019). "Recent advances in image recognition: A review." Pattern Recognition, 90, 119-149. DOI: 10.1016/j.patcog.2019.02.013.
Cheung, N. M., Cai, W., & Liu, S. (2019). "Remote sensing in environmental monitoring: A case study on deep learning for invasive species detection." Remote Sensing, 11(3), 314. DOI: 10.3390/rs11030314.
Dai, X., Yang, L., Yang, Y., Carbonell, J., Le, Q. V., & Salakhutdinov, R. (2022). "Neural architecture search for convolutional neural networks." Medical Image Analysis, 80, 101785. DOI: 10.1016/j.media.2022.101785.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2020). "An image is worth 16x16 words: Transformers for image recognition at scale." arXiv preprint arXiv:2010.11929.
Elsken, T., Metzen, J. H., & Hutter, F. (2021). "Neural architecture search: A survey." Journal of Machine Learning Research, 20(55), 1-21.
Kumar, N., Belhumeur, P. N., & Biswas, A. (2017). "A benchmark dataset for evaluating smartphone-based indoor localization solutions." IEEE Transactions on Mobile Computing, 16(7), 2078-2090. DOI: 10.1109/TMC.2016.2612872.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). "Deep learning." Nature, 521(7553), 436-444. DOI: 10.1038/nature14539.
Makau, C., Kariuki, S., & Akama, J. S. (2019). "Application of machine learning in wildlife conservation: A review." Journal of Wildlife Management, 83(1), 1-12. DOI: 10.1002/jwmg.21702.
Mgaya, C., Tarimo, R., & Kimaro, J. (2019). "Smart cities and data mining: A case study of Tanzania." International Journal of Scientific & Technology Research, 8(4), 2546-2552. DOI: 10.1016/j.jtbi.2020.110052.
Nguyen, V. T., Nhu, V. H., & Tuan, N. H. (2018). "Smart agriculture: An approach for agriculture management using image recognition." Journal of Computer Science and Cybernetics, 34(3), 259-275. DOI: 10.15625/1813-9663/34/3/11838.
Ogundipe, O., Adeyemo, O., & Oyeyemi, A. (2020). "Application of image recognition in healthcare for improved diagnostics." International Journal of Biomedical Imaging, 2020, Article ID 8574603. DOI: 10.1155/2020/8574603.
Pan, S. J., & Yang, Q. (2010). "A survey on transfer learning." IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359. DOI: 10.1109/TKDE.2009.191.
Real, E., Aggarwal, A., Huang, Y., & Le, Q. V. (2019). "Regularized evolution for image classifier architecture search." Proceedings of the AAAI Conference on Artificial Intelligence, 4780-4789.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). "ImageNet large scale visual recognition challenge." International Journal of Computer Vision, 115(3), 211-252. DOI: 10.1007/s11263-015-0816-y.
Singh, A., & Singh, A. (2020). "Role of image recognition technology in agriculture." International Journal of Engineering Research and Technology, 13(3), 717-722. DOI: 10.17577/IJERTV9IS030119.
Smith, A., Smith, B., & Johnson, C. (2018). "Deep learning: Improving accuracy for image recognition." Journal of Artificial Intelligence Research, 61, 1-20. DOI: 10.1613/jair.5623.
Snoek, J., Larochelle, H., & Adams, R. P. (2012). "Practical Bayesian optimization of machine learning algorithms." Proceedings of the 25th International Conference on Neural Information Processing Systems, 2951-2959.
Sun, X., Wu, P., Liu, Z., & Zhou, D. (2021). "Automated machine learning: Methods, systems, challenges." arXiv preprint arXiv:2106.02287.
Tan, M., & Le, Q. V. (2020). "EfficientNet: Rethinking model scaling for convolutional neural networks." Proceedings of the International Conference on Machine Learning (ICML), 6105-6114.
Tishby, N., & Zaslavsky, N. (2015). "Deep learning and the information bottleneck principle." IEEE Information Theory Workshop (ITW), 1-5. DOI: 10.1109/ITW.2015.7133162.
Tumwebaze, R., Kalule, J., & Namata, J. (2021). "Application of image recognition in wildlife conservation: A case of Uganda." Journal of Environmental Protection, 12(3), 301-310. DOI: 10.4236/jep.2021.123018.
Zhang, X., Zhang, H., Dai, J., Li, J., He, X., & Smola, A. J. (2020). "Adversarial AutoAugment." arXiv preprint arXiv:2001.02668.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Rina Suzuki
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
