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.
Modeling awareness is an important topic in the computer science as it is closely related to preparing systems that know what is needed (e.g. data accumulated or ignored, effector activated) to achieve a given goal. Preparing tools to build and compare dedicated or general aware computational systems can lead to step-by-step hierarchical construction of intelligent solutions. Within this text we show...
Training deep neural networks requires a large amount of memory, making very deep neural networks difficult to fit on accelerator memories. In order to overcome this limitation, we present a method to reduce the amount of memory for training a deep neural network. The method enables to suppress memory increase during the backward pass, by reusing the memory regions allocated for the forward pass....
The paper presents selected properties of the adaptive speed neural controller trained online for direct drive during mechanical changes of the object parameters. In the article was compared different algorithms for learning neural networks such as: backpropagation algorithm BP, momentum backpropagation MBP, Quickprop and RPROP. The authors proposed an effective method of supervision of learning neural...
Based on thermal acoustic data from the body tissue in upper arm that has been produced through thermal acoustic tomography method, classification system for the data has been built as a support of decision making about physiological abnormality. The advantages of the system built in this research is able to detect physiological abnormalities in the body tissues without the need for surgery (non-invasive...
We present an extension to a previously proposed Deep ELM architecture, and make the network end-to-end trainable using backpropagation. This significantly increases the network's performance for lower numbers of hidden units, and hence is well suited for resource constrained applications. The new architecture offers classification results of over 98% on the MNIST handwritten digits dataset for hidden...
Decision making tasks that involve processing of sequential stimuli with long delays pose a significant challenge to modeling using current methods in neural networks. However, decision making in animals involves storage of salient stimuli over long periods of time, robust maintenance of this information in the presence of noisy input, and subsequent recall and processing at the time of final decision...
The Paper proposes new complex-valued ELM. The main emphasis in designing the new Complex-valued ELM is to improve the classification accuracy and also to remove the drawbacks present in other complex-valued ELMs. A novel method of converting the input to complex domain has been proposed in which the real-valued feature is considered as a projection of complex number. Two random complex valued input-hidden...
Forest fires are a dangerous and devastating phenomenon. Being able to accurately predict the burned area of a forest fire could potentially limit human casualties as well as better prepare for the ensuing economical and ecological damage. A data set from the Montesinho Natural Park in Portugal provides a difficult regression task regarding the prediction of forest fire burn area due to the limited...
Character recognition technique associates a symbolic identity with the image of a character. Different characters and languages have different structures and features. Lampung character and language are different with any other languages. We have developed Lampung handwritten character recognition using back-propagation neural networks. However since some Lampung characters have similar features,...
In recent years, Neural Networks (NNs) have become widely popular for the execution of different machine learning algorithms. Training an NN is computationally intensive since it requires numerous multiplications of matrices that represent synaptic weights. It is therefore appealing to build a hardware-based NN accelerator to gain parallelism and efficient computation. Recently, we have proposed a...
Artificial Neural Network (ANN) forms a useful tool in pattern recognition tasks. Collection of five, eight or more cards in a cards game are normally called poker hands. There are various poker variations, each with different poker hands ranking. In the present paper, an attempt is made to solve poker hand classification problem using different learning paradigms and architectures of artificial neural...
Human face recognition and detection has become a very interesting field for the researcher and this interest is motivated by the huge demand of extensive applications of the real time surveillance system and the static matching system like DMV licenses, port authority and bank system. The image processing, neural network and computer vision are the most area active research areas. Many of papers...
The call center provides customer services to the customer of a company. Call center agents play an important role in such services. To ensure the quality of customer service, agent training and evaluation are essential. Usually, agents are monthly evaluated by their supervisor. Nevertheless, an objective evaluation standard is desired. Twenty three quantitative indicators for call center operations...
Estimation of depth in a Neural Network (NN) or Artificial Neural Network (ANN) is an integral as well as complicated process. In this article, we propose a way of using the transformation of functions combined with recursive nature to have an adaptive, transcursive algorithm to represent the backpropagation concept used in deep learning for a Multilayer Perceptron Network. Each function can be used...
Stomach is a digestive organ which is the most vulnerable to diseases which are caused by the increased stomach acid production due to wrong diet. Many people sometimes ignore, even worse underestimate this, but if it's been ignored too long, it will lead to death. Thus it's necessary for routine check to determine whether there is disturbance in the stomach organ or not. One simple way to check is...
In this paper, we explore the potential of using deep learning for extracting speaker-dependent features for noise robust speaker identification. More specifically, an SNR-adaptive denoising classifier is constructed by stacking two layers of restricted Boltzmann machines (RBMs) on top of a denoising deep autoencoder, where the top-RBM layer is connected to a soft-max output layer that outputs the...
Artificial neural networks are one of the most popular and promising areas of artificial intelligence research. Training data containing outliers are often a problem for supervised neural networks learning algorithms that may not always come up with acceptable performance. Many robust learning algorithms have been proposed so far to improve the performance of neural networks in the presence of outliers...
Query suggestions (QS) tailored specifically for children are slowly gaining research attention in response to the growth in Internet use by children. Even though QS offered by popular search engines adequately meet the information needs of the general public, they do not achieve equivalent effectiveness from a child's perspective. This is because children's search behaviors, interests, cognitive...
This paper presents the use of artificial neural networks (ANN) to determine the solution one of the classic applications of differential equations, the mixing tank problem. An artificial neural network with feed-forward backpropagation is designed to predict the concentration of substance in the tank at any time t. The network has three layers of structure 5 - 10 - 2 and used the Levenberg-Marquadt...
The aim of this paper is to investigate the estimation of the variation of ground resistance throughout the year by using artificial neural networks (ANNs). An ANN was trained, validated, and tested with different training algorithms by using experimental data of soil resistivity, ground resistance, and rainfall in order to select the optimum training algorithm and the respective parameters and predict...
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.