Random Neural Network Methods and Deep Learning

Abstract

The random neural network (RNN) is a mathematical model for an “integrate and fire” spiking network that closely resembles the stochastic behavior of neurons in mammalian brains. Since its proposal in 1989, there have been numerous investigations into the RNN's applications and learning algorithms. Deep learning (DL) has achieved great success in machine learning. Recently, the properties of the RNN for DL have been investigated, in order to combine their power. Recent results demonstrate that the gap between RNNs and DL can be bridged and the DL tools based on the RNN are faster and can potentially be used with less energy expenditure than existing methods.

Intrusion Detection Framework for the Internet of Things Using a Dense Random Neural Network

“…An RaNN mimics the behavior of biological neurons with its "integrate and fire" system. The RaNN is used in several applications including image processing, optimization, communication systems, cybersecurity, classification, and pattern recognition [16]. The RaNN has several key advantages.…”

“…Second, it has better generalization capabilities because of its probability constraints. Third, it has established mathematical properties that can simplify complex computations [16]. Fourth, it is an ideal algorithm for deployment in resource-constrained hardware and IoT devices because of its highly distributed nature [17], [18].…”

Generalized Deep Neural Network and its Application in Financial Time Series Forecasting

“…Compared with other methods, it has obvious advantages: The model can well solve the problem of redundant information in traditional research, and the algorithm has the characteristics of higher complexity in the learning process, slower computation speed and not easy to fall into local optimum or local minimal value. NARX network can well solve the problems that are difficult to be handled by traditional model algorithms, and NARX network has strong fault tolerance, which can make fast, effective and accurate prediction of data [5]. When facing the financial data with high noise, high intensity and strong interference, the traditional methods are difficult to achieve the desired effect, and the deep neural network can effectively use these complex data to predict the financial time series, which has greatly improved than the GRN network in the accuracy of processing data, and it can effectively solve the problems encountered by the traditional methods [6].Based on the above description, neural networks in forecasting can innovatively propose an intelligent hybrid forecasting method based on deep learning as well as locally homogenized indicators.…”