The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we propose a modified architecture of a Pi-Sigma Neural Network (PSNN) based on two modifications: extension of the activation function and adding delays to neurons in the hidden layer. These new networks are called respectively Activation Function Extended Pi-Sigma (AFEPS) and Delayed Pi-Sigma (DPS) are obtained first by adding an activation function to all hidden neurons and secondly...
How to develop an intelligent ventilator and control it well to provide a better experience and treatment effect for respiratory patients is still a difficult task needed to be solved. The existing problems focus on the control algorithm and the mechanical structure. Dedicated to these two problems, the paper proposes a design of CPAP ventilator based on the ANN algorithm. Firstly, the paper introduces...
Application of ANNs as a tool in proposed techniques has been developed. ANNs model of desired region's border allows to get more available information on the performance indices' behavior in the vicinity of the border. Enclosed in ANNs-model output calculation of recommended value for scanning step norm and of the performance indices gradient enables the use of ANNs-model as a source of important...
This article explores the problems of automated retail systems, which named are vending machines. The main problem is the formation of an assortment of a vending machine, the realization of which will bring maximum profit. As a modern analysis tool of consumer demand in retail trade artificial intelligence is regarded. Attention is focused on one of the methods of constructing artificial intelligence...
Training of Artificial Neural Networks (ANN) is an important step to make the network able to accomplish the desired task. This capacity of learning in such networks makes them applied in many applications as modeling and control. However, many of training algorithms have some drawbacks like: too many parameters to be estimated, important calculus time. In this paper, we propose a very simple method...
The development of a deep (stacked) convolutional auto-encoder in the Caffe deep learning framework is presented in this paper. We describe simple principles which we used to create this model in Caffe. The proposed model of convolutional auto-encoder does not have pooling/unpooling layers yet. The results of our experimental research show comparable accuracy of dimensionality reduction in comparison...
To overcome the unsatisfying trend prediction results of network public opinion in the present research, this paper put forward a method of Levenberg-Marquardt-based Back-Propagation (LM-BP) neural network algorithm to predict the network public opinion trend. Taking the microblog as the research object, the effectiveness and reliability of the method are proved with some real data in this article...
In this work, the potential application of Artificial Neural Network (ANN) was studied to predict the absorption of Carbon Dioxide (CO2) in Ionic Liquid (IL) solutions over wide-ranging operating conditions. A few physical properties had been chosen as input data which were temperature, partial pressure of CO2, molecular weight, acentric value, critical temperature and critical pressure of IL. A sample...
This paper presents an artificial neural network (ANN) model based design for Hénon chaotic systems, and its equivalent hardware model for hardware co-simulation using Field Programmable Gate Arrays (FPGA). Chaotic generators can be used for the study of chaotic behaviors of brain activities captured by Electroencephalogram (EEG). The ANN model is designed with different fixed-point data format and...
The problems arising in loop electrical network system is a relay setting that follows changes in the system such as power source operation, regular maintenance and damage to powers source. To obtain an adaptive relay which is capable of following the changes in the network system, this paper is proposes the modeling of the coordination of the power system network with the cascade forward neural network...
Hexacopter is a member of rotor-wing Unmanned Aerial Vehicle (UAV) which has 6 six rotors with fixed pitch blades and nonlinear characteristics that cause controlling the attitude of hexacopter is difficult. In this paper, Modified Elman Recurrent Neural Network (MERNN) is used to control attitude and altitude of Heavy-lift Hexacopter to get better performance than Elman Recurrent Neural Network (ERNN)...
This paper deals with a design methodology for a neural network with improved robust qualities in notion to handling uncertain input data space variations. The proposed network topology combines the simplicity of the radial basis functions networks to interpret or classify data pairs and the abilities of the intuitionistic fuzzy logic to deal with the vagueness of the data space. A simplified gradient...
The aim of the paper is to introduce a new approach for the Regions of Required Quality (RRQ) construction under the Control Systems computer-aided analysis and design. Application of the Artificial Neural Networks (ANNs) as a tool in the proposed techniques is represented under the title “Method of Sensitive Border”. The developed Neural network model of the RRQ-region's border allows one to get...
Analog integrated circuits may increase the neuromorphic network performance dramatically, leaving far behind their digital and biological counterparts, while approaching the energy efficiency of the brain. The key component of the most advanced analog circuit implementations is a nanodevice with adjustable conductance — essentially an analog nonvolatile memory cell, which could mimic synaptic transmission...
Recurrent neural networks are represented as non-linear models of dynamic systems. This kind of neural networks is divided into two groups, which are globally and locally recurrent neural networks. Some types are distinguished among globally recurrent networks. The major approximation properties and features of every distinguished type are emphasized. The represented analysis is useful for choosing...
Deep Learning methods have proven to be very successful in classifying large data sets of high feature dimensionality. However, their success usually implies very long training times. In this paper we examine learning methods combining the Random Neural Network, a biologically inspired neural network and the Extreme Learning Machine that achieve state of the art classification performance while requiring...
One of the most used neural network model for clustering data is the Self-Organizing Map (SOM). Over the years, it has been applied in many areas, from computing to biology, and therefore a wide range of data types have been considered. Originally, the SOM was developed to take real-valued data into account. Thus, learning other data types, such as binary and category data, remains a challenge. This...
In recent years, the research on neural networks has been guided by the search of new mathematical frameworks, with the hope of finding new features, as geometric interpretation, for facing today problems or reducing the computational cost. In this paper we introduce a new Clifford Neuron [1], extending the conformai neuron, presented in [2] through the generalization of the geometric algebra of quadratic...
A biological neural network is constituted by numerous subnetworks and modules with different functionalities. For an artificial neural network, the relationship between a network and its subnetworks is also important and useful for both theoretical and algorithmic research, i.e. it can be exploited to develop incremental network training algorithm or parallel network training algorithm. In this paper...
This paper presents two parallel implementationsof the Back-propagation algorithm, a widely used approach forArtificial Neural Networks (ANNs) training. These implementationspermit one to increase the number of ANNs trainedsimultaneously taking advantage of the thread-level massiveparallelism of GPUs and multi-core architecture of modernCPUs, respectively. Computational experiments are carried outwith...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.