Deep Learning Model Parameter Optimization Using Evolutionary Strategies

Authors

  • Sreenivas Mekala IT, Sreenidhi Institute of Science and Technology, Medchal malkajigiri, Hyderabad Telangana
  • Atowar Ul Islam Associate professor, Computer Science, University of Science and Technology, Meghalaya. Ri-bhoi 9th Mile Meghalaya
  • Mandeep Kaur Assistant Professor, Electronics and Communication Engineering, Department of Electronics and Communication Engineering, Punjabi University, Patiala Punjab
  • C. Punitha Devi Associate Professor, Department of Banking Technology Pondicherry University Puducherry
  • Bhabani Sankar Gouda Asst. Professor, Computer Science and Engineering, NIST Institute of Science and Technology, BPUT, Ganjam, Berhampur Odisha

Keywords:

Evolutionary Strategies, Deep Learning, Parameter Optimization, Performance Metrics, Computational Efficiency

Abstract

The effectiveness of evolutionary techniques for deep learning model parameter optimization is investigated in this study. By utilizing a variety of datasets and architectures, such as CNNs, RNNs, CIFAR-10, MNIST, as well as CNNs, the study assesses how well evolutionary methodologies perform in contrast to conventional gradient-based optimization techniques. The outcomes of our study exhibit a steady increase in model accuracy, precision, and recall, in addition to F1 score on various tasks, indicating the adaptability of evolutionary techniques in augmenting deep learning capabilities. Evolutionary techniques accelerate the optimization process by achieving greater fitness levels in early generations, according to the convergence rate study. The study also highlights the computational effectiveness of evolutionary techniques, solving a crucial issue in practical applications by attaining competitive performance with less computing time. The work highlights the flexibility of evolutionary methods including their potential to transform parameter tuning procedures, adding to the larger knowledge of optimization techniques in the deep learning environment. Evolutionary techniques are presented in this article as potentially useful tools for practitioners and scholars looking for practical methods that are effective deep neural networks.

Downloads

Download data is not yet available.

References

ABBASSI, R., SAIDI, S., UROOJ, S., BILAL, N.A., ALAWAD, M.A. and PREMKUMAR, M., 2023. An Accurate Metaheuristic Mountain Gazelle Optimizer for Parameter Estimation of Single- and Double-Diode Photovoltaic Cell Models. Mathematics, 11(22), pp. 4565.

ALGHAMDI, H., HAFEEZ, G., ALI, S., ULLAH, S., KHAN, M.I., MURAWWAT, S. and LYU-GUANG HUA, 2023. An Integrated Model of Deep Learning and Heuristic Algorithm for Load Forecasting in Smart Grid. Mathematics, 11(21), pp. 4561.

CĂTĂLINA-LUCIA COCIANU, USCATU, C.R., KOFIDIS, K., MURARU, S. and VĂDUVA, A.G., 2023. Classical, Evolutionary, and Deep Learning Approaches of Automated Heart Disease Prediction: A Case Study. Electronics, 12(7), pp. 1663.

CHEN, Y., SHEN, X., ZHANG, G. and LU, Z., 2023. Multi-Objective Multi-Satellite Imaging Mission Planning Algorithm for Regional Mapping Based on Deep Reinforcement Learning. Remote Sensing, 15(16), pp. 3932.

DATTA, G., JOSHI, N. and GUPTA, K., 2023. Hyper-parameter optimization in neural-based translation systems: A case study. International Journal on Smart Sensing and Intelligent Systems, 16(1),.

FANG, J., RAO, Y. and SHI, M., 2023. A deep reinforcement learning algorithm for the rectangular strip packing problem. PLoS One, 18(3),.

FENG, J., SHI, T., WU, Y., XIE, X., HE, H. and TAN, H., 2023. Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy. Sensors, 23(10), pp. 4659.

FENG, Z., LIU, G., WANG, L., GU, Q. and CHEN, L., 2023. Research on the Multiobjective and Efficient Ore-Blending Scheduling of Open-Pit Mines Based on Multiagent Deep Reinforcement Learning. Sustainability, 15(6), pp. 5279.

IBRAHIM, R., GHNEMAT, R. and QASEM ABU AL-HAIJA, 2023. Improving Alzheimer’s Disease and Brain Tumor Detection Using Deep Learning with Particle Swarm Optimization. Ai, 4(3), pp. 551.

ISMAIL, W.N., FATHIMATHUL RAJEENA, P.P. and ALI, M.A.S., 2023. A Meta-Heuristic Multi-Objective Optimization Method for Alzheimer’s Disease Detection Based on Multi-Modal Data. Mathematics, 11(4), pp. 957.

LU, C., YANG, J., LEIRA, B.J., CHEN, Q. and WANG, S., 2023. Three-Dimensional Path Planning of Deep-Sea Mining Vehicle Based on Improved Particle Swarm Optimization. Journal of Marine Science and Engineering, 11(9), pp. 1797.

MATITOPANUM, S., PITAKASO, R., SETHANAN, K., SRICHOK, T. and CHOKANAT, P., 2023. Prediction of the Ultimate Tensile Strength (UTS) of Asymmetric Friction Stir Welding Using Ensemble Machine Learning Methods. Processes, 11(2), pp. 391.

MU, G., LIAO, Z., LI, J., QIN, N. and YANG, Z., 2023. IPSO-LSTM hybrid model for predicting online public opinion trends in emergencies. PLoS One, 18(10),.

PAL, S., JHANJHI, N.Z., AZMI, S.A., AKILA, D., ALSUBAEI, F.S. and ABDULALEEM, A.A., 2023. An Intelligent Task Scheduling Model for Hybrid Internet of Things and Cloud Environment for Big Data Applications. Sustainability, 15(6), pp. 5104.

PENG, S., ZHU, J., LIU, Z., HU, B., WANG, M. and PU, S., 2023. Prediction of Ammonia Concentration in a Pig House Based on Machine Learning Models and Environmental Parameters. Animals, 13(1), pp. 165.

SARWAT, A. and WANI, M.A., 2023. Gradient-Based Neural Architecture Search: A Comprehensive Evaluation. Machine Learning and Knowledge Extraction, 5(3), pp. 1176.

SUN, Y., HUANG, Q., LIU, T., CHENG, Y. and LI, Y., 2023. Multi-Strategy Enhanced Harris Hawks Optimization for Global Optimization and Deep Learning-Based Channel Estimation Problems. Mathematics, 11(2), pp. 390.

TRAN, M., PHAM-HI, D. and BUI, M., 2023. Optimizing Automated Trading Systems with Deep Reinforcement Learning. Algorithms, 16(1), pp. 23.

XU, B., DENG, J., LIU, X., CHANG, A., CHEN, J. and ZHANG, D., 2023. A Review on Optimal Design of Fluid Machinery Using Machine Learning Techniques. Journal of Marine Science and Engineering, 11(5), pp. 941.

ZHOU, J., WANG, H., XIAO, C. and ZHANG, S., 2023. Hierarchical Surrogate-Assisted Evolutionary Algorithm for Integrated Multi-Objective Optimization of Well Placement and Hydraulic Fracture Parameters in Unconventional Shale Gas Reservoir. Energies, 16(1), pp. 303.

ABBAS, F., ZHANG, F., ISMAIL, M., KHAN, G., IQBAL, J., ABDULWAHED, F.A. and MOHAMMED, F.A., 2023. Optimizing Machine Learning Algorithms for Landslide Susceptibility Mapping along the Karakoram Highway, Gilgit Baltistan, Pakistan: A Comparative Study of Baseline, Bayesian, and Metaheuristic Hyperparameter Optimization Techniques. Sensors, 23(15), pp. 6843.

BACANIN, N., STOEAN, C., ZIVKOVIC, M., RAKIC, M., ROMA STRULAK-WÓJCIKIEWICZ and STOEAN, R., 2023. On the Benefits of Using Metaheuristics in the Hyperparameter Tuning of Deep Learning Models for Energy Load Forecasting. Energies, 16(3), pp. 1434.

BAHRIYE, A., DERVIS, K. and RUSTU, A., 2022. A comprehensive survey on optimizing deep learning models by metaheuristics. The Artificial Intelligence Review, 55(2), pp. 829-894.

CHIEH-HUANG, C., JUNG-PIN, L., YU-MING, C., CHI-JU, L. and PING-FENG PAI, 2023. A Study of Optimization in Deep Neural Networks for Regression. Electronics, 12(14), pp. 3071.

CORTACERO, K., MCKENZIE, B., MÜLLER, S., KHAZEN, R., LAFOURESSE, F., CORSAUT, G., VAN ACKER, N., FRENOIS, F., LAMANT, L., MEYER, N., VERGIER, B., WILSON, D.G., LUGA, H., STAUFER, O., DUSTIN, M.L., VALITUTTI, S. and CUSSAT-BLANC, S., 2023. Evolutionary design of explainable algorithms for biomedical image segmentation. Nature Communications, 14(1), pp. 7112.

EJIGU, T.H., KEKEBA, K., MARTÍNEZ-BALLESTEROS, M. and MARTÍNEZ-ÁLVAREZ, F., 2023. A Bayesian Optimization-Based LSTM Model for Wind Power Forecasting in the Adama District, Ethiopia. Energies, 16(5), pp. 2317.

HAFEZ, I. and DHAOUADI, R., 2023. Identification of Mechanical Parameters in Flexible Drive Systems Using Hybrid Particle Swarm Optimization Based on the Quasi-Newton Method. Algorithms, 16(8), pp. 371.

LIN, Z., PENG, C., TAN, W. and HE, X., 2023. Image Adversarial Example Generation Method Based on Adaptive Parameter Adjustable Differential Evolution. Entropy, 25(3), pp. 487.

MAYURI ARUL, V.R., MANOHARAN, R.K., SUBRAMANI, N., ARIDOSS, M. and MOHAMMAD, G.G., 2023. Robust Facial Expression Recognition Using an Evolutionary Algorithm with a Deep Learning Model. Applied Sciences, 13(1), pp. 468.

SENAÏ, B., SIDI AHMED, H.R. and KHIAT, S., 2023. An Optimized Hybrid Model of Convolutional Neural Networks and eXtreme Gradient Boosting for Enhanced Mammographic Tumor Classification. Ingenierie des Systemes d'Information, 28(3), pp. 725-736.

Downloads

Published

24.03.2024

How to Cite

Mekala, S. ., Islam, A. U. ., Kaur, M. ., Devi, C. P. ., & Gouda, B. S. . (2024). Deep Learning Model Parameter Optimization Using Evolutionary Strategies. International Journal of Intelligent Systems and Applications in Engineering, 12(19s), 145–152. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/5054

Issue

Vol. 12 No. 19s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.