Abstract
Building well-performing neural network models often require a large amount of real data. However, synthetic datasets are favoured as the collection of real data often brings up privacy and data security issues. This paper aims to build a shallow neural network model for the pre-trained synthetic feature dataset, VehicleX. Using genetic algorithm to reduce the dimensional complexity by randomly selecting a subset of features from before training. Furthermore, distinctiveness pruning techniques are used to reduce the network structure and attempt to find the optimal hidden neuron size. Both techniques improve the model performance in terms of test accuracy. The baseline model achieves 36.07% classification accuracy. Integrating genetic algorithm and the distinctiveness pruning achieve approximately 37.26% and 36.12% respectively while combining both methods achieve 37.31%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Buhrmester, V., Münch, D., Arens, M.: Analysis of explainers of black box deep neural networks for computer vision: A survey. arXiv preprint arXiv:1911.12116 (2019)
Chandakkar, P.S., Li, Y., Ding, P.L.K., Li, B.: Strategies for re-training a pruned neural network in an edge computing paradigm. In: 2017 IEEE International Conference on Edge Computing (EDGE), pp. 244–247. IEEE (2017)
El-Maaty, A.M.A., Wassal, A.G.: Hybrid GA-PCA feature selection approach for inertial human activity recognition. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1027–1032. IEEE (2018)
Gedeon, T.D.: Indicators of hidden neuron functionality: the weight matrix versus neuron behaviour. In: Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, pp. 26–29. IEEE (1995)
Gedeon, T.D., Harris, D.: Network reduction techniques. In: Proceedings International Conference on Neural Networks Methodologies and Applications, vol. 1, pp. 119–126 (1991)
Kakoulli, E., Soteriou, V., Theocharides, T.: Intelligent hotspot prediction for network-on-chip-based multicore systems. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 31(3), 418–431 (2012)
Kim, E., Gopinath, D., Pasareanu, C., Seshia, S.A.: A programmatic and semantic approach to explaining and debugging neural network based object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11128–11137 (2020)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Li, B., Zhang, T., Xia, T.: Vehicle detection from 3d lidar using fully convolutional network. arXiv preprint arXiv:1608.07916 (2016)
Nowruzi, F.E., Kapoor, P., Kolhatkar, D., Hassanat, F.A., Laganiere, R., Rebut, J.: How much real data do we actually need: Analyzing object detection performance using synthetic and real data. arXiv preprint arXiv:1907.07061 (2019)
Ou, G., Murphey, Y.L.: Multi-class pattern classification using neural networks. Pattern Recogn. 40(1), 4–18 (2007)
Rodriguez, J.D., Perez, A., Lozano, J.A.: Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 569–575 (2009)
Sehgal, S., Singh, H., Agarwal, M., Bhasker, V., et al.: Data analysis using principal component analysis. In: 2014 International Conference on Medical Imaging, M-Health and Emerging Communication Systems (MedCom), pp. 45–48. IEEE (2014)
Sharma, S., Sharma, S.: Activation functions in neural networks. Towards DataScience 6(12), 310–316 (2017)
Tang, Z., et al.: Pamtri: pose-aware multi-task learning for vehicle re-identification using highly randomized synthetic data. In: Proceedings of the IEEE/CVF Inter-national Conference on Computer Vision, pp. 211–220 (2019)
Yao, Y., Zheng, L., Yang, X., Naphade, M., Gedeon, T.: Simulating content consistent vehicle datasets with attribute descent. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 775–791. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_46
Zhu, M., Gupta, S.: To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, L., Fu, YS. (2021). Genetic Algorithm and Distinctiveness Pruning in the Shallow Networks for VehicleX. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13108. Springer, Cham. https://doi.org/10.1007/978-3-030-92185-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-92185-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92184-2
Online ISBN: 978-3-030-92185-9
eBook Packages: Computer ScienceComputer Science (R0)