Learning in the feed-forward random neural network: A critical review

Since the early 1990s, Random Neural Networks (RNNs) have gained importance in the Neural Networks and Queueing Networks communities. RNNs are inspired by biological neural networks and they are also an extension of open Jackson's networks in Queueing Theory. In 1993, a learning algorithm of gradient type was introduced in order to use RNNs in supervised learning tasks. This method considers only the weight connections among the neurons as adjustable parameters. All other parameters are deemed fixed during the training process. The RNN model has been successfully utilized in several types of applications such as: supervised learning problems, pattern recognition, optimization, image processing, associative memory. In this contribution we present a modification of the classic model obtained by extending the set of adjustable parameters. The modification increases the potential of the RNN model in supervised learning tasks keeping the same network topology and the same time complexity of the algorithm. We describe the new equations implementing a gradient descent learning technique for the model.

The two primary measures of land mine detection performance are the probability of detection P/sub d/ and the probability of false alarm P/sub fa/. These two measures are highly inter-dependent and must be evaluated together. The relationship between the two probabilities directly affects the overall performance of the sensor in the field. In this paper we introduce a novel false alarm non-parametric filter based on the random neural network (RNN) model and the /spl delta/-technique. The study is based on mine detection using electromagnetic induction (EMI) sensors. The minefield data are pre-processed via the /spl delta/-technique before applying it to the RNN. The RNN has a predefined structure that tries to implement a mapping close enough in some precise sense to the discrimination function between non-mine and mine patterns. Limited numbers of non-mine and mine patterns, extracted from a small calibration area for a certain minefield provided by DARPA, are used for training the RNN. We show that the RNN gives effective decisions on patterns measured on other locations using different EMI sensor. The results show that the RNN produces a probability of detection up to 100 per cent with a substantial reduction of false alarms over the /spl delta/-technique (up to 40 per cent false alarm filtering).

Long Term Evolution (LTE) is the preliminary version of a fourth generation (4G) mobile communication system. Its aim is to support different services with high data rates and strict Quality of Experience (QoE) requirements of users. The main aim of this study is to present a prediction model based on Random Neural Networks (RNNs) for objective, non-intrusive prediction of video quality over LTE for video applications. A three layer feed-forward RNN model with gradient descent training algorithm has been developed. This model uses a combination of objective parameters in the application and network layers, such as Content Type (CT), Sender Bit Rate (SBR), resolution size, Frame Rate (FR), codec, and packet loss rate (PLR). The video quality was predicted in terms of the Mean Opinion Score (MOS). The results show an approximate 50% increase in accuracy using this model, compared to previous models. LTE-Sim software has been used to generate different samples for testing and training RNN model.

This paper presents the Random Neural Network in a Deep Learning Cluster structure with a new learning algorithm based on the genetics according to the genome model, where information is transmitted in the combination of genes rather than the genes themselves. The proposed genetic model transmits information to future generations in the network weights rather than the neurons. The innovative genetic algorithm is implanted in a complex deep learning structure that emulates the human brain: Reinforcement Learning takes fast local current decisions, Deep Learning Clusters provide identity and memory, Deep Learning Management Clusters take final strategic decisions and finally Genetic Learning transmits the information learned to future generations. This proposed structure has been applied and validated in Fintech; a Smart Investment application: an Intelligent Banker that performs Buy and Sell decisions on several Assets with an associated market and risk. Our results are promising; we have connected the human brain and genetics with Machine Learning based on the Random Neural Network model where biology; similar as Artificial Intelligence is learning gradually and continuously while adapting to the environment.

The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference.

Real-time occupancy monitoring information is an important component in building energy management and security. Advances in technology enables us to develop vision-based systems. These systems have gained popularity among different scientific research communities due to their high accuracy. Based on real-time video from a single camera, people occupancy rates in buildings can be correctly estimated using neural network models. This paper proposes an intelligent real-time bidirectional system, using Random Neural Network (RNN) predictions. An overhead camera was used to capture RGB images and the number of people crossing a virtual line was counted using the proposed counting technique. The proposed algorithm extracts some important features such as occupant blob areas, major axis, minor axis, eccentricity, perimeters and area-perimeter ratio for total 1000 frames. Finally, a RNN model is trained with aforementioned features using a gradient decent algorithm. Real-time experimental results show the effectiveness of the proposed method, especially when occupants are in group and blob merge/split scenarios. Real-time testing revealed an accuracy between 100 and 93.38% for single and multiple occupants, respectively.

Artificial intelligence model for predicting geomechanical characteristics using easy-to-acquire offset logs without deploying logging tools

In recent years, hydroforming has become the topic of a lot of active research. Researchers have been looking for better procedures and prediction tools to improve the quality of the product and reduce the prototyping cost. Similar to any other metal forming process, hydroforming leads to non-homogeneous plastic deformations of the workpiece. In this paper, a model is developed to predict the amount of deformation caused by hydroforming using random neural networks (RNNs). RNNs learn the behavior of a system from the provided input/output data in a manner similar to the way the human brain does. This is different from the usual connectionist neural network (NN) models which are based on simple functional analyses. Experimental data is collected and used in training as well as testing the RNNs. The RNN models have feedforward architectures and use a generalized learning algorithm in the training process. Multi-layer RNNs with as few as six neurons were used to capture the nonlinear correlations between the input and output data collected from an experimental setup. The RNN models were able to predict the center deflection, the thickness variation, as well as the deformed shape of circular plate specimens with good accuracy.

Journal Article The Random Neural Network: A Survey Get access Stelios Timotheou Stelios Timotheou * Intelligent Systems and Networks Group, Department of Electrical and Electronic Engineering, Imperial College, London SW7 2BT, UK *Corresponding author: stelios.timotheou05@imperial.ac.uk Search for other works by this author on: Oxford Academic Google Scholar The Computer Journal, Volume 53, Issue 3, March 2010, Pages 251–267, https://doi.org/10.1093/comjnl/bxp032 Published: 30 April 2009 Article history Received: 01 November 2008 Revision received: 17 February 2009 Published: 30 April 2009

The advancement in technologies such as Artificial Intelligence (AI) and the Internet of Things (IoT) has enabled the development of a variety of healthcare applications and services such as Remote Health Monitoring (RHM). Developing an RHM system requires integrating various medical sensors that generate a vast amount of data. The integration of AI and Machine Learning (ML) models in the RHM system for analysis of the medical data can enable the development of a decision support system that can reduce costs and save valuable time for clinicians and caregivers. This thesis is focused on leveraging ML and AI technique sto address the challenges in RHM with a specific emphasis on improving the performance of AI-based decision support systems. This is achieved by addressing limitations in current AI-based models and developing novel Random Neural Network (RNN)-based models for fall detection and epilepsy detection and prediction. Initially the thesis presents a literature review on state-of-the-art machine learning techniques used in remote healthcare solutions, automatic fall activity recognition for elderly populations, and epileptic seizure detection and prediction. Furthermore, the study presents a novel fall detection method based on RNN. The results obtained from the proposed model are compared with traditional classification algorithms such as Artificial Neural Networks, Convolutional Neural Networks, and state-of-the-art fall detection schemes. The proposed RNN-based method demonstrates significant improvements in accuracy compared to other methods. The proposed scheme achieved an overall accuracy of 98% in detecting falls. Additionally, several other parameters such as precision, recall, specificity, and F-measure show that the proposed algorithm has better generalization capabilities when compared with other traditional machine learning schemes. Furthermore, the proposed RNN is also compared with a recent scheme and the obtained results demonstrate the superiority of the proposed scheme. Additionally, the thesis presents two novel RNN-based classification schemes for detecting epileptic seizures. In the first scheme statistical features are extracted from raw EEG data, while the second method incorporates frequency analysis techniques such as Discrete Wavelet Transform (DWT) and Fast Fourier Transform. The performance of these models is evaluated and compared with other classification algorithms, demonstrating the effectiveness of RNN-based models for epilepsy detection. Finally, a novel RNN-based epilepsy prediction model is proposed for classification of EEG data into three classes i.e. ictal, pre-ictal, and inter-ictal. The model pre-processes the EEG data by decomposing the signals into five frequency sub-bands using DWT. After pre-processing, six statistical features are extracted from each frequency sub-band which a reused as an input vector to train the RNN model. The proposed scheme achieves an overall accuracy of 95.66% in seizure prediction, outperforming other state-of-the-art models.

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.

Storage and Recognition Methods for The Random Neural Network

Recent work demonstrated the value of multi clusters of spiking Random Neural Networks (RNN) with dense soma-to-soma interactions in deep learning. In this paper we go back to the original simpler structure and we investigate the power of single RNN cells for deep learning. First, we consider three approaches with the single cells, twin cells and multi-cell clusters. This first part shows that RNNs with only positive parameter can conduct convolution operations similar to those of the convolutional neural network. We then develop a multi-layer architecture of single cell RNNs (MLSRNN), and show that this architecture achieves comparable or better classification at lower computation cost than conventional deep-learning methods.

We have developed RNNI, a global alignment method for protein-protein interaction networks between species, using a random neural network model (RNN) tailored for the alignment problem. The benchmark of the method in comparison with other available alignment approaches was performed using a range of measurements. The alignment results of the human and yeast pair showed that RNNI is capable of generating alignments with large conserved networks with functionally-related protein pairs while maintaining the closeness to the naive- sequence homology approach (BLAST).

Deep Learning Clusters in the Cognitive Packet Network