Abstract
In order to improve the output precision of depth neural networks, an improved teaching and learning optimization algorithm is proposed to optimize the weights and thresholds of depth neural networks. The algorithm is improved according to the teaching and learning phases of the basic teaching and learning algorithms. The performance of the algorithm is tested by electro-discharge machining (EDM) experiments. The results show that the algorithm has the advantages of fast convergence and high solution accuracy.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Sze V, Chen YH, Yang TJ, Emer J (2017) Efficient processing of deep neural networks: a tutorial and survey
Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2016) A survey of deep neural network architectures and their applications ☆. Neurocomputing 234:11–26
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85
Mandal D, Pal SK, Saha P (2007) Modeling of electrical discharge machining process using back propagation neural network and multi-objective optimization using non-dominating sorting genetic algorithm-ii. J Mater Process Tech 186(1–3):154–162
Ming W, Ma J, Zhang Z, Huang H, Shen D, Zhang G et al (2016) Soft computing models and intelligent optimization system in electro-discharge machining of sic/al composites. Int J Adv Manuf Technol:1–17
Xiuli MA, Teng K (2016) Process parameter optimization of ti-6al-4v electric discharge machining based on bp neural network l-m algorithm. Mater Rev
Anitha J, Dasa R, Pradhan MK (2016) Multi-objective optimization of electrical discharge machining processes using artificial neural network. Jordan J Mech Ind Eng 10(1)
Velázquez-Iturbide JA, Debdi O, Paredes-Velasco M (2015) A review of teaching and learning through practice of optimization algorithms
Rao RV, Patel V (2012) An elitist teaching-learning-based optimization algorithm for solving complex constrained optimization problems. Int J Ind Eng Comput 3(4):535–560
Rao RV, Savsani VJ, Vakharia DP (2011) Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems. Comput Aided Des 43(3):303–315
Rao RV, Kalyankar VD, Waghmare G (2014) Parameters optimization of selected casting processes using teaching–learning-based optimization algorithm. Appl Math Model 38(23):5592–5608
Liu J, Gong M, Miao Q, Wang X, Li H (2017) Structure learning for deep neural networks based on multiobjective optimization. IEEE Trans Neural Netw Learn Syst PP(99):1–14
Warghat ST, Deshmukh TR (2017) Parameter optimization of milling operation using teaching-learning-based optimization and artificial neural network. MAYFEB J Mech Eng 1
Kankal M, Uzlu E (2016) Neural network approach with teaching–learning-based optimization for modeling and forecasting long-term electric energy demand in Turkey. Neural Comput Appl:1–11
Shouheng T (2013) A modified teaching-learning-based optimization algorithm and application in neural networks. Caai Trans Intell Syst 8(4):327–332
Theodoridis S (2015) Chapter 18—neural networks and deep learning. Mach Lear:875–936
Maity K, Mishra H (2016) Ann modelling and elitist teaching learning approach for multi-objective optimization of µ-EDM. J Intell Manuf:1–18
Wang H, Shao F, Li H, Wang X, Li X, Department ME et al (2016) Optimization of electrical parameter in electrical discharge machining of engineering ceramics based on fuzzy neural network. Mod Manufact Eng
Napitupulu R, Wahyudi A, Soepangkat BOP (2015) Performance characteristics optimization of electrical discharge machining process using back propagation neural network and genetic algorithm 25(3)
Rao RV (2016) Multiobjective optimization of machining processes using NSTLBO algorithm. In: Teaching learning based optimization algorithm. Springer International Publishing
Wang C, Wang Y, Wang K, Dong Y, Yang Y (2017) An improved hybrid algorithm based on biogeography/complex and metropolis for many-objective optimization. Math Probl Engineering 2017 (2017-3-30):1–14
Acknowledgements
This research work was supported by National natural science foundation of china (No.51475150) and Key Laboratory of Automotive Power Train and Electronics (Hubei University of Automotive Technology, No.ZDK1201703).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, C., Li, B., Wang, Y., Wang, K., Wang, S. (2018). A Modified Teaching and Learning Based Optimization Algorithm and Application in Deep Neural Networks Optimization for Electro-Discharge Machining. In: Wang, K., Wang, Y., Strandhagen, J., Yu, T. (eds) Advanced Manufacturing and Automation VII. IWAMA 2017. Lecture Notes in Electrical Engineering, vol 451. Springer, Singapore. https://doi.org/10.1007/978-981-10-5768-7_64
Download citation
DOI: https://doi.org/10.1007/978-981-10-5768-7_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-5767-0
Online ISBN: 978-981-10-5768-7
eBook Packages: EngineeringEngineering (R0)