Training a Feed-Forward Neural Network Using Cuckoo Search

Cuckoo Search (CS) is a nature-inspired and metaheuristic algorithm which is based on a brood reproductive strategy of cuckoo birds to increase their population. This algorithm mainly serves to determine the maximum or minimum value of a particular problem which is known as the objective function. CS has reportedly outperformed other nature-inspired algorithms in terms of computational efficiency and the speed of convergence to reach an optimal solution. This chapter aims at exploring the application of CS to determine the parameters of Artificial Neural Networks (ANN). The inherent problem with traditional training of ANNs using backpropagation is that the learning process cannot guarantee a global minimum solution and has a tendency of getting trapped in local minima. The working of such ANN models is restricted to a differentiable neuron transfer function. The CS algorithm has been observed to provide a solution without the use of derivates to optimize such convoluted problems. The usage of ANNs across a wide range of problems including classification tasks, image processing, signal processing, etc. justifies the application of CS to the backpropagation procedure of ANNs to achieve a faster rate of convergence and avoid the local minima problem. This chapter also presents discussions and results on how ANNs optimized with variants of CS perform when applied to the detection of chronic kidney disease, modelling of operating photovoltaic module temperature and forest type classification.

[1]  Zhenxing Zhang,et al.  An Improved Cuckoo Search Algorithm with Adaptive Method , 2014, 2014 Seventh International Joint Conference on Computational Sciences and Optimization.

[2]  Bhekisipho Twala,et al.  An adaptive Cuckoo search algorithm for optimisation , 2018, Applied Computing and Informatics.

[3]  Ajith Abraham,et al.  Artificial neural networks , 2005 .

[4]  Nilanjan Dey,et al.  Electrical Energy Output Prediction Using Cuckoo Search Based Artificial Neural Network , 2018 .

[5]  Zulkifli Othman,et al.  Cuckoo search for determining Artificial Neural Network training parameters in modeling operating photovoltaic module temperature , 2014, Proceedings of 2014 International Conference on Modelling, Identification & Control.

[6]  Soumya Sen,et al.  Cuckoo search coupled artificial neural network in detection of chronic kidney disease , 2017, 2017 1st International Conference on Electronics, Materials Engineering and Nano-Technology (IEMENTech).

[7]  Jemal H. Abawajy,et al.  Neural Network Training by Hybrid Accelerated Cuckoo Particle Swarm Optimization Algorithm , 2014, ICONIP.

[8]  Ashraf Osman Ibrahim,et al.  Artificial Neural Network Weight Optimization: A Review , 2014 .

[9]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[10]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[11]  Zeng Meng,et al.  Improved Cuckoo Search Algorithm for Solving Inverse Geometry Heat Conduction Problems , 2019 .

[12]  Jun Wang,et al.  An Improved Cuckoo Search Optimization Algorithm for the Problem of Chaotic Systems Parameter Estimation , 2016, Comput. Intell. Neurosci..

[13]  Nilanjan Dey,et al.  Application of cuckoo search in water quality prediction using artificial neural network , 2017, Int. J. Comput. Intell. Stud..

[14]  Xin-She Yang,et al.  Cuckoo Search via Lévy flights , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[15]  Jesada Kajornrit.  A comparative study of optimization methods for improving artificial neural network performance , 2015, 2015 7th International Conference on Information Technology and Electrical Engineering (ICITEE).