Fortified Cuckoo Search Algorithm on training multi-layer perceptron for solving classification problems

被引：2

作者：

Thirugnanasambandam K. ^{[1
]}

Prabu U. ^{[2
]}

Saravanan D. ^{[3
]}

Anguraj D.K. ^{[4
]}

Raghav R.S. ^{[5
]}

机构：

[1] Centre for Smart Grid Technologies, School of Computer Science and Engineering, Vellore Institute of Technology, Tami Nadu, Chennai Campus, Chennai

[2] Department of Computer Science and Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Andhra Pradesh, Vijayawada

[3] Department of Computer Science Engineering, VIT Bhopal University, Bhopal-Indore Highway, Madhya Pradesh, Bhopal

[4] Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, Guntur

[5] School of Computing, SASTRA Deemed University, Tamil Nadu, Thanjavur

来源：

Personal and Ubiquitous Computing | 2023年 / 27卷 / 03期

关键词：

Classification; Cuckoo Search Algorithm; FNN; Machine learning; Multi-layer perception; Multi-layer perceptron; Neural network; Optimization;

D O I：

10.1007/s00779-023-01716-1

中图分类号：

学科分类号：

摘要：

Multi-layer perceptron (MLP) in artificial neural networks (ANN) is one among the trained neural models which can hold several layers as a hidden layer for intensive training to obtain optimal results. On the other hand, the classification problem has a high level of attraction towards researchers to increase the accuracy in classification. In ANN, feedforward neural network (FNN) is one model that possesses the art of solving classification and regression problems. When input data is given to FNN, it will apply the sum of product rule and the activation function to map the input with its appropriate output. In the sum of product rule, a term called weights is to be chosen appropriately to map between the input and output. In standard FNN, the weights are chosen in a random way which may lead to slower convergence towards the optimal choice of weight values. In this paper, an effective optimization model is proposed to optimize the weights of MLP of FNN for effective classification problems. Four different datasets were chosen, and the results are interpreted with statistical performance measures. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

引用

页码：1039 / 1049

页数：10

共 39 条

[1] Mangasarian O.L., Wolberg W.H., Cancer diagnosis via linear programming, (1990)
[2] Rosenblatt F., The perceptron, a perceiving and recognizing automaton project para, (1957)
[3] McCulloch W.S., Pitts W., A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biol., 5, (1943)
[4] Thirugnanasambandam K., Prakash S., Subramanian V., Et al., Appl Intell, 49, (2019)
[5] Werbos P., Beyond regression: new tools for prediction and analysis in the behavioral sciences, (1974)
[6] Patricia Melin P., Sanchez D., Castillo O., Genetic optimization of modular neural networks with fuzzy response integration for human recognition, Inform Sci, 197, pp. 1-19, (2012)
[7] Guo Z.X., Wong W.K., Li M., Sparsely connected neural network-based time series forecasting, Inform. Sci, 193, pp. 54-71, (2012)
[8] Gardner M.W., Dorling S.R., Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences, Atmos Environ, 32, pp. 2627-2636, (1998)
[9] Barakat M., Lefebvre D., Khalil M., Druaux F., Mustapha O., Parameter selection algorithm with self adaptive growing neural network classifier for diagnosis issues, Int J Mach Learn Cybern, 4, 3, pp. 217-233, (2013)
[10] Csaji B.C., Approximation with artificial neural networks, (2001)

← 1 2 3 4 →