Abstract
The work addresses the problem of integration of deep learning and genetic algorithms (GA). An approach is developed where the GA directly modifies the training datasets rather than adjusting the parameters of the trained neural network. These datasets consist of records capturing the agent's behavior in the environment and are treated as genotypes within the GA framework. The resulting phenotypes are the trained neural networks themselves. Importantly, the architecture and hyperparameters of the neural network and its learning model remain unchanged throughout the process. Numerical experiments conducted using the “Three Cowboys” game paradigm provide evidence supporting the concept and demonstrate the effectiveness of the proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Levy, E., David, O.E., Netanyahu, N.S.: Genetic algorithms and deep learning for automatic painter classification. In: Proceedings of the 16th Genetic and Evolutionary Computation Conference: GECCO 2014, pp. 1143–1150. Association for Computing Machinery, Vancouver, BC (2014). https://doi.org/10.1145/2576768.2598287
Young, S.R., Rose, D.C., Karnowski, T.P., Lim, S.H., Patton, R.M.: Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: Workshop on Machine Learning in High-Performance Computing Environments: MLHPC 2015, Article 4. P. 1–5. Association for Computing Machinery (2015). https://doi.org/10.1145/2834892.2834896
Erden, C.: Genetic algorithm-based hyperparameter optimization of deep learning models for PM25 time-series prediction. Int. J. Environ. Sci. Technol. 20, 2959–2982 (2023)
Majidi, M., Toroghi, R.M.: A combination of multi-objective genetic algorithm and deep learning for music harmony generation. Multimedia Tools Appl. 82(2), 2419–2435 (2023). https://doi.org/10.1007/s11042-022-13329-6
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Boston, MA (2016)
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., Mordatch, I.: Emergent Tool Use from Multi-Agent Interaction. ar**v:1909.07528 (2020)
Baker, J.E.: Reducing bias and inefficiency in the selection algorithm. In: Grefenstette, J.J. (ed.). Genetic Algorithms and their Applications: Proceedings of the Second International Conference on Genetic Algorithms. Psychology Press, New York (1987)
Samsonovich, A.V., De Jong, K.A., Kitsantas, A., Peters, E.E., Dabbagh, N., Kalbfleisch, M.L.: Cognitive constructor: an intelligent tutoring system based on a biologically inspired cognitive architecture (BICA). Front. Artif. Intell. Appl. 171(1), 311–325 (2008)
Acknowledgments
This work is supported by the Russian Science Foundation Grant No. 22-11-00213.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nazarko, M.Y., Fedorov, K.A., Samsonovich, A.V. (2024). Deep Learning Evolution: Using Genetic Algorithm to Modify Training Datasets. In: Samsonovich, A.V., Liu, T. (eds) Biologically Inspired Cognitive Architectures 2023. BICA 2023. Studies in Computational Intelligence, vol 1130. Springer, Cham. https://doi.org/10.1007/978-3-031-50381-8_66
Download citation
DOI: https://doi.org/10.1007/978-3-031-50381-8_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50380-1
Online ISBN: 978-3-031-50381-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)