期刊名称：Journal of King Saud University @?C Computer and Information Sciences
印刷版ISSN：1319-1578
出版年度：2019
页码：1-7
DOI：10.1016/j.jksuci.2019.09.007
出版社：Elsevier
摘要：Replicator Neural Network (RNN) is a popular algorithm for anomaly detection, but finding optimal number of hidden layers and then finding optimal number of neurons in each hidden layer is quite a challenging and time-consuming task. Extreme Learning Machines (ELM) are neural networks with single-hidden layer but the learning algorithm is different and faster than back-propagation. ELM-based RNNs solve our problem of determining the number of hidden layers and the learning algorithm is also faster than gradient-descent based RNN. The problem of identifying the optimal number of neurons in the hidden layer can be solved by Garson algorithm. In this work, the author propose an optimal Replicator Neural Network which is optimized using ELM learning and Garson algorithm for anomaly detection. The experimental results show that the proposed method is fast as well as highly accurate.
关键词：Anomaly detection ; Big data ; Garson algorithm ; Replicator neural network ; Extreme learning machine
