Abstract
Feedforward neural network (FNN) emerges as a promising machine learning algorithm widely used for crucial tasks such as prediction, classification, clustering, regression, and etc. due to its excellent performance in training, learning and organizing data. Conventional approaches such as gradient-based algorithm is commonly used to train FNNs, but it has drawbacks of being trapped into local optima easily, slow convergence rate and high sensitivity to initial solutions generated. Metaheuristic search algorithm such as teaching-learning-based optimization (TLBO) is envisioned as a potential solution to train FNNs due to their stochastic nature and excellent global search ability. In this paper, a new TLBO variant named as teaching-learning-based optimization with modified learning phases (TLBO-MLPs) is designed as the training algorithm of FNN, aiming to optimize its neuron weights, biases and selection of activation functions by referring to the datasets of given classification problems. The classification performances of FNN trained by TLBO-MLPs are evaluated by using the real-life classification datasets from UCI Machine Learning Repository and compared with those optimized by the other well-established TLBO variants. Rigorous simulation studies show that the FNN trained by TLBO-MLPs outperforms most of its peer algorithms significantly in solving different classification problems. Particularly, the FNN classifiers optimized by proposed TLBO-MLPs are reported to outperform its competitors up to 15.72% and 29.07% in terms of classification accuracy for both training and testing datasets, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carvalho M, Ludermir TB (2007) Particle swarm optimization of neural network architectures and weights. In: 7th international conference on hybrid intelligent systems (HIS 2007). IEEE, pp 336–339
Rodriguez P, Wiles J, Elman JL (1999) A recurrent neural network that learns to count. Connection Sci 11:5–40
Sumachev A, Kuzmin V, Borodin E (2018) River flow forecasting using artificial neural networks. Int J Mech Eng Technol 9:706–714
Sainath TN, Mohamed A-R, Kingsbury B, Ramabhadran B (2013) Deep convolutional neural networks for LVCSR. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 8614–8618
Syulistyo AR, Purnomo DMJ, Rachmadi MF, Wibowo A (2016) Particle swarm optimization (PSO) for training optimization on convolutional neural network (CNN). Jurnal Ilmu Komputer dan Informasi 9:52–58
Vt SE, Shin YC (1994) Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems. IEEE Trans Neural Netw 5:594–603
Wu H, Zhou Y, Luo Q, Basset MA (2016) Training feedforward neural networks using symbiotic organisms search algorithm. In: Computational intelligence and neuroscience 2016
Feng J, Lu S (2019) Performance analysis of various activation functions in artificial neural networks. J Phys Conf Ser 022030
Mirjalili S, Hashim SZM, Sardroudi HM (2012) Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Appl Math Comput 218:11125–11137
Tarkhaneh O, Shen H (2019) Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search. Heliyon 5:e01275
Ang KM, Lim WH, Isa NAM, Tiang SS, Wong CH (2020) A constrained multi-swarm particle swarm optimization without velocity for constrained optimization problems. Expert Syst Appl 140:112882
Al-Sanabani DGA, Solihin MI, Pui LP, Astuti W, Ang CK, Hong LW (2019) Development of non-destructive mango assessment using handheld spectroscopy and machine learning regression. J Phys Conf Ser 012030
Yao L, Shen J-Y, Lim WH (2016) Real-time energy management optimization for smart household. In: 2016 IEEE international conference on internet of things (iThings) and IEEE green computing and communications (GreenCom) and IEEE cyber, physical and social computing (CPSCom) and IEEE smart data (SmartData). IEEE, pp 20–26
Yao L, Damiran Z, Lim WH (2017) Energy management optimization scheme for smart home considering different types of appliances. In: 2017 IEEE international conference on environment and electrical engineering and 2017 IEEE industrial and commercial power systems Europe (EEEIC/I&CPS Europe). IEEE, pp 1–6
Yao L, Lim WH (2017) Optimal purchase strategy for demand bidding. IEEE Trans Power Syst 33:2754–2762
Yao L, Lim WH, Tiang SS, Tan TH, Wong CH, Pang JY (2018) Demand bidding optimization for an aggregator with a genetic algorithm. Energies 11:2498
Yao L, Yao L, Lim WH (2018) A soft curtailment of wide-area central air conditioning load. Energies 11:492
Yao L, Chen Y-Q, Lim WH (2015) Internet of things for electric vehicle: an improved decentralized charging scheme. In: 2015 IEEE international conference on data science and data intensive systems. IEEE, pp 651–658
Natarajan E, Kaviarasan V, Lim WH, Tiang SS, Parasuraman S, Elango S (2019) Non-dominated sorting modified teaching–learning-based optimization for multi-objective machining of polytetrafluoroethylene (PTFE). J Intell Manuf 1–25
Yu L, Tarawni MA, Ahmad SH, Al-Banawi O, Batiha MA (2015) High performance thermoplastic elastomer (TPE) nanocomposite based on graphene nanoplates (GNPs). World J Eng 12(5):437–442
Yu LJ, Sahrim AH, Kong I, Mouad AT (2012) Microwave absorbing properties of nickel-zinc ferrite/multiwalled nanotube thermoplastic natural rubber composites. In: Advanced materials research. Trans Tech Publ, pp 24–28
Yu L-J, Ahmad SH, Kong I, Tarawneh MA, Flaifel MH (2013) Preparation and characterisation of NiZn ferrite/multiwalled nanotubes thermoplastic natural rubber composite. Int J Mater Eng Innovation 2(4):214–224
Yu L-J, Ahmad SH, Kong I, Appadu S (2012) Sifat magnet, mikrostruktur dan morfologi komposit getah asli termoplastik berpengisi ferit NiZn/Mwnt. Sains Malaysiana 41:453–458
Chong OT, Lim WH, Isa NAM, Ang KM, Tiang SS, Ang CK (2020) A teaching-learning-based optimization with modified learning phases for continuous optimization. In: Science and information conference. Springer, Berlin, pp 103–124
Ang KM, Lim WH, Isa NAM, Tiang SS, Ang CK, Natarajan E, Solihin MI (2020) A constrained teaching-learning-based optimization with modified learning phases for constrained optimization. J Adv Res Dyn Control Syst 12:15
Kiranyaz S, Ince T, Yildirim A, Gabbouj M (2009) Evolutionary artificial neural networks by multi-dimensional particle swarm optimization. Neural Netw 22:1448–1462
Rao RV, Savsani VJ, Vakharia DP (2011) Teaching-learning-based optimization: a novel method for constrained mechanical design optimization problems. Comput Aided Des 43:303–315
Yu K, Wang X, Wang Z (2016) Constrained optimization based on improved teaching–learning-based optimization algorithm. Inf Sci 352:61–78
Savsani VJ, Tejani GG, Patel VK (2016) Truss topology optimization with static and dynamic constraints using modified subpopulation teaching–learning-based optimization. Eng Optim 48:1990–2006
Zheng H, Wang L, Zheng X (2017) Teaching-learning-based optimization algorithm for multi-skill resource constrained project scheduling problem. Soft Comput 21:12
Benali A, Hachama M, Bounif A, Nechnech A, Karray M (2019) A TLBO-optimized artificial neural network for modeling axial capacity of pile foundations. Eng Comput 1–10
Wang L, Zou F, Hei X, Yang D, Chen D, Jiang Q (2014) An improved teaching-learning-based optimization with neighborhood search for applications of ANN. Neurocomputing 143:231–247
Li K, Xie X, Xue W, Dai X, Chen X, Yang X (2018) A hybrid teaching-learning artificial neural network for building electrical energy consumption prediction. Energy Build 174:323–334
Zou F, Chen D, Xu Q (2019) A survey of teaching–learning-based optimization. Neurocomputing 335:366–383
Akhtar J, Koshul BB, Awais MM (2013) A framework for evolutionary algorithms based on Charles Sanders Peirce’s evolutionary semiotics. Inf Sci 236:93–108
Shao W, Pi D, Shao Z (2017) An extended teaching-learning based optimization algorithm for solving no-wait flow shop scheduling problem. Appl Soft Comput 61:193–210
Tizhoosh HR (2005) Reinforcement learning based on actions and opposite actions. In: International conference on artificial intelligence and machine learning
Roy PK, Sur A, Pradhan DK (2013) Optimal short-term hydro-thermal scheduling using quasi-oppositional teaching learning based optimization. Eng Appl Artif Intell 26:2516–2524
MartÃn GarcÃa JA, Gil Mena AJ (2013) Optimal distributed generation location and size using a modified teaching–learning based optimization algorithm. Int J Electr Power Energy Syst 50:65–75
Ouyang H-B, Gao L-Q, Kong X-Y, Zou D-X, Li S (2015) Teaching-learning based optimization with global crossover for global optimization problems. Appl Math Comput 265:533–556
Cao J, Luo J (2015) A study on SVM based on the weighted elitist teaching-learning-based optimization and application in the fault diagnosis of chemical process. In: MATEC web of conferences. EDP Sciences, p 05016
Satapathy SC, Naik A, Parvathi K (2013) Weighted teaching-learning-based optimization for global function optimization. Appl Math 4:429
Wu Z-S, Fu W-P, Xue R (2015) Nonlinear inertia weighted teaching-learning-based optimization for solving global optimization problem. Intell Neurosci 2015:87–87
Kandasamy T, Rajendran R (2018) Hybrid algorithm with variants for feed forward neural network. Int Arab J Inf Technol 15:240–245
Uzlu E, Kankal M, Akpınar A, Dede T (2014) Estimates of energy consumption in Turkey using neural networks with the teaching–learning-based optimization algorithm. Energy 75:295–303
Lin G, Shen W (2018) Research on convolutional neural network based on improved Relu piecewise activation function. Procedia Comput Sci 131:977–984
Xue Y, Tang T, Liu AX (2019) Large-scale feedforward neural network optimization by a self-adaptive strategy and parameter based particle swarm optimization. IEEE Access 7:52473–52483
Derrac J, GarcÃa S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1:3–18
GarcÃa S, Molina D, Lozano M, Herrera F (2009) A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: a case study on the CEC’2005 special session on real parameter optimization. J Heuristics 15:617
Rao RV, Patel V (2013) An improved teaching-learning-based optimization algorithm for solving unconstrained optimization problems. Scientia Iranica 20:710–720
Zou F, Chen D, Wang J (2016) An improved teaching-learning-based optimization with the social character of PSO for global optimization. Comput Intell Neurosci 2016
Mahmoodabadi M, Ostadzadeh R (2019) CTLBO: Converged teaching-learning-based optimization. Cogent Eng 6:1654207
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ang, K.M., Lim, W.H., Tiang, S.S., Ang, C.K., Natarajan, E., Ahamed Khan, M.K.A. (2022). Optimal Training of Feedforward Neural Networks Using Teaching-Learning-Based Optimization with Modified Learning Phases. In: Isa, K., et al. Proceedings of the 12th National Technical Seminar on Unmanned System Technology 2020. Lecture Notes in Electrical Engineering, vol 770. Springer, Singapore. https://doi.org/10.1007/978-981-16-2406-3_65
Download citation
DOI: https://doi.org/10.1007/978-981-16-2406-3_65
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2405-6
Online ISBN: 978-981-16-2406-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)