Hybrid Wolf-Bat Algorithm for Optimization of Connection Weights in Multi-layer Perceptron

In a neural network, the weights act as parameters to determine the output(s) from a set of inputs. The weights are used to find the activation values of nodes of a layer from the values of the previous layer. Finding the ideal set of these weights for training a Multi-layer Perceptron neural network such that it minimizes the classification error is a widely known optimization problem. The presented article proposes a Hybrid Wolf-Bat algorithm, a novel optimization algorithm, as a solution to solve the discussed problem. The proposed algorithm is a hybrid of two already existing nature-inspired algorithms, Grey Wolf Optimization algorithm and Bat algorithm. The novel introduced approach is tested on ten different datasets of the medical field, obtained from the UCI machine learning repository. The performance of the proposed algorithm is compared with the recently developed nature-inspired algorithms: Grey Wolf Optimization algorithm, Cuckoo Search, Bat Algorithm, and Whale Optimization Algorithm, along with the standard Back-propagation training method available in the literature. The obtained results demonstrate that the proposed method outperforms other bio-inspired algorithms in terms of both speed of convergence and accuracy.

[1]  Manuel P. Cuéllar,et al.  Energy consumption forecasting based on Elman neural networks with evolutive optimization , 2018, Expert Syst. Appl..

[2]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[3]  S. Tiwari,et al.  Nature inspired algorithms on Industrial applications : A survey , 2018 .

[4]  Heejin Cho,et al.  Artificial neural network (ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery , 2018 .

[5]  Václav Snásel,et al.  Metaheuristic design of feedforward neural networks: A review of two decades of research , 2017, Eng. Appl. Artif. Intell..

[6]  Hossam Faris,et al.  Training feedforward neural networks using multi-verse optimizer for binary classification problems , 2016, Applied Intelligence.

[7]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[8]  Xin-She Yang,et al.  A New Metaheuristic Bat-Inspired Algorithm , 2010, NICSO.

[9]  Hossam Faris,et al.  Automatic selection of hidden neurons and weights in neural networks using grey wolf optimizer based on a hybrid encoding scheme , 2019, International Journal of Machine Learning and Cybernetics.

[10]  Václav Snásel,et al.  Ensemble of heterogeneous flexible neural trees using multiobjective genetic programming , 2017, Appl. Soft Comput..

[11]  Atulya K. Nagar,et al.  Advances in Nature-Inspired Computing and Applications , 2019, EAI/Springer Innovations in Communication and Computing.

[12]  Ashish Khanna,et al.  Optimized Binary Bat algorithm for classification of white blood cells , 2019, Measurement.

[13]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[14]  Seyed Mohammad Mirjalili.  How effective is the Grey Wolf optimizer in training multi-layer perceptrons , 2014, Applied Intelligence.

[15]  M. Valipour.  Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms , 2016 .

[16]  Hossam Faris,et al.  Optimizing connection weights in neural networks using the whale optimization algorithm , 2016, Soft Computing.

[17]  Sushil Kumar,et al.  Hybrid Nature-Inspired Algorithms: Methodologies, Architecture, and Reviews , 2018 .

[18]  Fernando de la Prieta,et al.  Artificial neural networks used in optimization problems , 2018, Neurocomputing.

[19]  Abdul Razak Hamdan,et al.  Optimization of neural network model using modified bat-inspired algorithm , 2015, Appl. Soft Comput..

[20]  Hossam Faris,et al.  Improved monarch butterfly optimization for unconstrained global search and neural network training , 2018, Applied Intelligence.

[21]  Christian Blum,et al.  An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training , 2007, Neural Computing and Applications.

[22]  Hossam Faris,et al.  An efficient hybrid multilayer perceptron neural network with grasshopper optimization , 2018, Soft Computing.

[23]  Achintya Das,et al.  Analysis of a Nature Inspired Firefly Algorithm based Back-propagation Neural Network Training , 2012, ArXiv.