Method of Artificial Neural Networks Teaching
Journal Title: Webology - Year 2020, Vol 17, Issue 1
Abstract
The technique of artificial neural networks training has been developed. A distinctive feature of the proposed technique is that it provides training not only for the synaptic weights of the artificial neural network but also for the type and parameters of the membership function. If it is impossible to provide, the specified quality of functioning of artificial neural networks due to the learning of the parameters of the artificial neural network, the architecture of artificial neural networks is trained. The choice of architecture, type and parameters of the membership function takes into account the computing resources of the tool and taking into account the type and amount of information that is coming to the input of an artificial neural network. Also, while using the proposed method, there is no accumulation of error learning artificial neural networks as a result of processing information, which is supplied to the input of artificial neural networks. The development of the proposed methodology is due to the need to train artificial neural networks, in order to process more information, with the uniqueness of the made decisions. According to the results of the research, it is established that the mentioned training method provides on average 16-23 percent higher efficiency of training of artificial neural networks and does not accumulate errors during training. This technique will allow to train artificial neural networks; identify effective measures to improve the performance of artificial neural networks. Also, the developed technique will increase the efficiency of the functioning of artificial neural networks by learning the parameters and architecture of artificial neural networks. The technique proposed by the authors reduces the use of computing resources for support and decision-making systems. Using the developed methodology will develop measures that are aimed at improving the efficiency of artificial neural networks training and increase the speed of the processing information.
Authors and Affiliations
Khudhair Abed Thamer
Keywords
Related Articles
- EP ID EP687835
- DOI 10.14704/WEB/V17I1/a207
- Views 201
- Downloads 0
Software planning and scheduling in software management
In software management effective project planning and scheduling is essential. Inability to design and additionally helpless administration can cause postponements and costs that, given planning and spending limitations,...
Managing online identity and diverse social networks on Facebook
This paper reports research that examined use of Facebook to (consciously or unconsciously) create an online identity. An online survey (N=752) was conducted during Phase 1 of the research. Results of Phase 1 informed...
Improvement of methodical approaches to higher schools' marketing activity assessment on the basis of Internet technologies application
The paper substantiates the necessity of higher schools marketing activity developing on the basis of Internet technologies; suggests the technique of comprehensive assessment of functioning and quality of the site as th...
Bridging the Mire between E-Research and E-Publishing for Multimedia Digital Scholarship in the Humanities and Social Sciences: An Australian Case Study
Digital media developments confront the humanities and social sciences with major challenges in exploiting multimedia rich data sets. A critical need is demonstrated to bridge the divide between the building of multimedi...
How to use recommender systems in e-business domains
Recommender systems (RS) were developed by research as a means to manage the information retrieval problem for users searching large databases. Recently they have become very popular among businesses as online marketing...