Тип публикации: статья из журнала
Год издания: 2018
Ключевые слова: semi-supervised learning, genetic algorithms, artificial neural networks, self-configuration, automated generation
Аннотация: Semi-supervised techniques based on using both labelled and unlabelled examples can be an efficient tool for solving real-world problems with large amounts of unlabelled data. The usual method of solving such problems demands the long work of human experts in its initial stages to prepare the learning data, a process which includesПоказать полностьюsuch complex tasks as the labelling of large numbers of examples. In this case, it is not necessary to label all of these many examples, but just a few of them. In this paper, a new self-configuring genetic algorithm (SelfCGA) for the automated design of semi-supervised artificial neural networks (ANN) is presented. Firstly, the performance and behaviour of the proposed semi-supervised ANNs were studied under common experimental settings and their workability was established. Then their efficiency was evaluated on a real-world problem.
Журнал: International Journal on Information Technologies and Security
Выпуск журнала: Т. 10, № 2
Номера страниц: 111-118
ISSN журнала: 13138251
Место издания: Sofia