International Journal of Electrical and Computer Engineering (IJECE) Vol. 11, No. 6, December 2021, pp. 5277~5285 ISSN: 2088-8708, DOI: 10.11591/ijece.v11i6.pp5277-5285  5277 Journal homepage: http://ijece.iaescore.com Using the modified k-mean algorithm with an improved teaching-learning-based optimization algorithm for feedforward neural network training Morteza Jouyban 1 , Mahdie Khorashadizade 2 1 Department of Computer Science, Allameh Tabataba’i University, Tehran, Iran 2 Department of Computer Science, Sistan and Baluchestan University, Zahedan, Iran Article Info ABSTRACT Article history: Received Aug 16, 2020 Revised May 19, 2021 Accepted Jun 11, 2021 In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy of artificial neural network outputs after determining the proper structure for each problem depends on choosing the appropriate method for determining the best weights, which is the appropriate training algorithm. If the training algorithm starts from a good starting point, it is several steps closer to achieving global optimization. In this paper, we present an optimization strategy for selecting the initial population and determining the optimal weights with the aim of minimizing neural network error. Teaching-learning-based optimization (TLBO) is a less parametric algorithm rather than other evolutionary algorithms, so it is easier to implement. We have improved this algorithm to increase efficiency and balance between global and local search. The improved teaching-learning- based optimization (ITLBO) algorithm has added the concept of neighborhood to the basic algorithm, which improves the ability of global search. Using an initial population that includes the best cluster centers after clustering with the modified k-mean algorithm also helps the algorithm to achieve global optimum. The results are promising, close to optimal, and better than other approach which we compared our proposed algorithm with them. Keywords: K-mean clustering Neural network Teaching-learning algorithm This is an open access article under the CC BY-SA license. Corresponding Author: Morteza Jouyban Department of Computer Science Allameh Tabataba’i University Tehran, Iran Email: m.jouyban@gmail.com 1. INTRODUCTION Artificial neural networks (ANN) are new computational methods and systems for machine learning, knowledge demonstration, and ultimately the application of knowledge to oversee the output of complex systems. The main idea of networks is inspired by the way the biological neural system to process data and information in order to learn and create knowledge. The main philosophy of the artificial neural network is to model the processing characteristics of the human brain to approximate the usual computational methods with the biological processing method. In other words, the artificial neural network is a method that learns the communication knowledge between several sets of data through training and saves it for use in similar cases. This processor works in two ways similar to the human brain: Learning the neural network is done through training, and weighting in the neural network is similar to the information storage system of the human brain. With the help of computer programming knowledge, it is possible to design a data structure that