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.
Neural network architecture designed for large-scale and the generalization is poor, presents a neural network algorithm for fast pruning based on significance analysis. The essence of the method is based on large-scale neural network perceptron as the research object, the constructor error curved surface model to analyze the network connection weights of disturbance on the network output error caused...
This paper aims to present a comparison between probabilistic and deterministic spiking neural network for a back Propagation classification algorithm. To have a fair comparison, neuron models and structures are considered identical in both of the networks. The networks are trained and tested with the Iris database. According to the simulation results, the probabilistic network converges faster than...
Spirometric pulmonary function test is a wellestablished test in clinical medicine for the assessment of respiratory diseases. It measures the volume of air inhaled or exhaled as a function of time during forced breathing maneuvers and generates large data set. However, spirometric investigation is often prone to incomplete data sets due to inability of the children and patient to perform this test...
The usage of IEEE 802.15.4, Wireless Sensor Networks in our daily life has shown exponential growth in the past decade. Localization of wireless sensor networks is the most critical aspects of this network. One of the major models used in localization, uses Multilayered Perceptron for training its data. This paper focuses on the impact of various MLP training functions on range based localization...
Power generation of photovoltaic panels (PVP) depends mainly on the cell temperature (T) and the solar irradiance (G). Moreover, for a given climatic condition, the operating point is sensitive to the PVP connected load. To enable the PVP to generate the maximum of available power, many maximum power point trackers (MPPT) algorithms are developed. This paper presents an assessment of four main used...
Grid-Connected Photovoltaic (GCPV) system is a type of photovoltaic (PV) systems which has been widely used as a renewable-based electricity generation. Nevertheless, the intermittency and fluctuation in weather conditions have caused inconsistent and varying output performance of a GCPV system. This paper presents a Multi-Layer Feedforward Neural Network (MLFNN) model for predicting the AC power...
The article introduces a new technique for process modeling. On the basis of the fact that once nonlinear problem is modeled by piecewise-linear model, it can be solved by many efficient techniques, the result of introduced technique provides a set of linear equations. Each of these equations is valid in some region of state space and together, they approximate whole nonlinear process.
With increasing core counts in Chip Multi-Processor (CMP) designs, the size of the on-chip communication fabric and shared Last-Level Caches (LLC), which we term uncore here, is also growing, consuming as much as 30% of die area and a significant portion of chip power budget. In this work, we focus on improving the uncore energy-efficiency using dynamic voltage and frequency scaling. Previous approaches...
The human auditory system perceives sound in a much different manner than sound is measured by modern audio sensing systems. The most commonly referenced aspects of auditory perception are loudness and pitch which relate to the objective measures of frequency and sound pressure levels. This paper describes an efficient and accurate method for the conversion of the sensed factors of frequency and sound...
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...
Deep neural networks comprise several hidden layers of units, which can be pre-trained one at a time via an unsupervised greedy approach. A whole network can then be trained (fine-tuned) in a supervised fashion. One possible pre-training strategy is to regard each hidden layer in the network as the input layer of an auto-encoder. Since auto-encoders aim to reconstruct their own input, their training...
Development of modern technologies is related to an increasing complexity of the objects controled and hence the systems controlling them. In the most cases, automatic control systems consist of different nonlinear elements that significantly limit the capabilities of classical control theory in designing controllers. In recent decades, the methodology of neural networks has been increasingly used...
Feed forward Multilayer Perceptron (MLP) Neural Networks are universal approximators. Weight adjustment of the connectionist model is crucial to architectures that model systems behavior. This paper developed a neural network for hydrological purposes. Two architectures were developed, investigated, and tested for forecasting rainfall in the rain-fed Sectors in Sudan. A monthly architecture and a...
In most recent Intelligent Video Surveillance systems, mechanisms to support human decisions are integrated in cognitive artificial processes. These algorithms mainly address the problem of extraction and modelling of relevant information from a sensor network. In crowd monitoring the main problem is to individuate specific events as for example different behaviours among interacting entities. A bio-inspired...
Face recognition is a topic of great interest in different areas, especially those related to security. The identification of a person by the image of her face is a difficult task because of changes experienced by the face due to various factors, such as facial expression, aging and even the lighting. This paper presents a new face recognition technique based on the combination of a competitive fuzzy...
The purpose of this study is the prediction of Standard & Poor's (S&P500) trends (ups and downs) with macroeconomic variables, technical indicators, and investor moods using k-NN algorithm and probabilistic neural networks. More precisely, eleven economic factors, twelve technical indicators and four measures of investor's mood were selected as potential predictive variables. Then, the Granger...
SpikeProp is a supervised learning algorithm for spiking neural networks analogous to backpropagation. Like backpropagation, it may fail to converge for particular networks, parameters and datasets. However there are several behaviours and additional failure modes unique to SpikeProp which have not been explicitly outlined in the literature. These factors hinder the adoption of SpikeProp for general...
Topology design of artificial neural networks (AANs) is a complex problem. This paper presents a study of some approaches which derived from a pruning technique (OBS). In the first step, we explicit the corresponding algorithms used to determine the adequate number of neurons and weights for neural structure. In the second step, a comparative study of the presented strategies is also investigated...
The opportunity of application neuronetwork technologies in a IP-telephony is considered. The basic stages of an engineering technique of construction neuronetwork models are selected on the basis of an adaptive neural network.
Researchers in the field of Neuromorphic Engineering are looking at ways to reduce the chip space required to mimic the huge processing capacity of the human brain and to simplify algorithms to train it. Since the recent fabrication of a memristor by the Hewlett Packard Company, there is a possibility to achieve both of these. With their crucial hysteresis properties, memristors can store charge during...
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.