Development of a method for training artificial neural networks for intelligent decision support systems
Development of a method for training artificial neural networks for intelligent decision support systems
复制标题
开发用于智能决策支持系统的人工神经网络训练方法
DOI：
10.15587/1729-4061.2020.203301
复制
发表时间：
2020
影响因子：
--
通讯作者：
Tetiana Holenkovska
中科院分区：
文献类型：
--
作者：
Qasim Abbood Mahdi;A. Shyshatskyi;O. Symonenko;Nadiia Protas;Oleksandr Trotsko;V. Kyvliuk;A. Shulhin;Petro Steshenko;Eduard Ostapchuk;Tetiana Holenkovska
我们开发了一种用于智能决策支持系统的人工神经网络训练方法。该方法的一个显著特点是不仅训练人工神经网络的突触权值，而且训练隶属函数的类型和参数。在无法通过训练人工神经网络的参数来保证人工神经网络的给定功能质量的情况下，对人工神经网络的结构进行了训练。隶属函数的结构、类型和参数的选择是基于设备的计算资源，并考虑到人工神经网络输入信息的类型和数量。所开发的方法的另一个显著特点是不需要预先计算数据来计算输入数据。该方法的发展是由于智能决策支持系统需要训练人工神经网络，以便在做出明确决策的同时处理更多信息。研究结果表明，该训练方法训练人工神经网络的效率平均提高10 - 18%，且不积累训练误差。该方法将允许通过训练参数和结构来训练人工神经网络，确定提高人工神经网络效率的有效措施。该方法可以减少决策支持系统计算资源的使用，制定提高人工神经网络训练效率的措施，提高人工神经网络信息处理效率。
We developed a method of training artificial neural networks for intelligent decision support systems. A distinctive feature of the proposed method consists in training not only the synaptic weights of an artificial neural network, but also the type and parameters of the membership function. In case of impossibility to ensure a given quality of functioning of artificial neural networks by training the parameters of an artificial neural network, the architecture of artificial neural networks is trained. The choice of architecture, type and parameters of the membership function is based on the computing resources of the device and taking into account the type and amount of information coming to the input of the artificial neural network. Another distinctive feature of the developed method is that no preliminary calculation data are required to calculate the input data. The development of the proposed method is due to the need for training artificial neural networks for intelligent decision support systems, in order to process more information, while making unambiguous decisions. According to the results of the study, this training method provides on average 10–18 % higher efficiency of training artificial neural networks and does not accumulate training errors. This method will allow training artificial neural networks by training the parameters and architecture, determining effective measures to improve the efficiency of artificial neural networks. This method will allow reducing the use of computing resources of decision support systems, developing measures to improve the efficiency of training artificial neural networks, increasing the efficiency of information processing in artificial neural networks.