Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
We discuss several ways to accelerate genetic algorithm-based instance selection, where the two objectives are a minimal number of training instances and maximal accuracy of the classifier (we use neural networks) on the test data. We discuss several ways to accelerate the process, but we especially focus on two parameters: fitness function and chromosome length reduction. We evaluate different fitness...
A novel projection twin support vector machine (PTSVM), termed as NPTSVM, is presented in this paper for binary classification. Although this method determines two projection vectors using the same way as PTSVM, it has more advantages than existing PTSVMs. First, NPTSVM does not have to calculate inverse matrices during the learning process, which makes the training speed of NPTSVM be much faster...
Approximations and redundancies allow mobile and distributed applications to produce answers or outcomes of lesser quality at lower costs. This paper introduces RAPID, a new programming framework and methodology for service-based applications with approximations and redundancies. Finding the best service configuration under a given resource budget becomes a constrained, dual-weight graph optimization...
There are many challenges in single-channel multi-person mixed speech separation, such as modeling the temporal continuity of the speech signals and improving the frame separation performance simultaneously. In this paper, a separation method based on Deep Clustering with local optimization by the improved Non-Negative Matrix Factorization (NMF) combined with Factorial Conditional Random Fields (FCRF)...
Feature selection is addressed an important problem in data mining. To be high dimension of the data obtained from the sources is encountered as an issue in many issues such as computation cost. For this reason, eliminating the unnecessary ones among these data and choosing the appropriate ones makes it possible to evaluate the information correctly. In this study, it is tried to suggest a method...
Possible approaches to building the information and mathematical models to evaluate of the effectiveness and quality of the University are discussed in this paper. We characterize cycle of university management, determine the factors affecting the performance activity of universities, identify indicators of assessment of effectiveness and quality, formulate the problem of university management through...
Neural networks have demonstrated promising results for a wide range of applications. The proposed techniques employ different architectures and objective functions to adapt to the application while enabling a feasible implementation. Commonly used objective functions for network optimization are based on the cross entropy between the empirical distribution of the training data and the model distribution...
Demand is mounting in the industry for scalable GPU-based deep learning systems. Unfortunately, existing training applications built atop popular deep learning frameworks, including Caffe, Theano, and Torch, etc, are incapable of conducting distributed GPU training over large-scale clusters.To remedy such a situation, this paper presents Nexus, a platform that allows existing deep learning frameworks...
Recent research in computed tomographic imaging has focused on developing techniques that enable reduction of the X-ray radiation dose without loss of quality of the reconstructed images or volumes. While penalized weighted-least squares (PWLS) approaches have been popular for CT image reconstruction, their performance degrades for very low dose levels due to the inaccuracy of the underlying WLS statistical...
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition. SHDL framework is constructed with a multi-layer ScatterNet front-end, an unsupervised learning middle, and a supervised learning back-end module. Each layer of the SHDL network is automatically designed as an explicit optimization problem leading...
Traditional domain adaptation methods attempted to learn the shared representation for distribution matching between source domain and target domain where the individual information in both domains was not characterized. Such a solution suffers from the mixing problem of individual information with the shared features which considerably constrains the performance for domain adaptation. To relax this...
Deep structured of Convolutional Neural Networks (CNN) has recently gained intense attention in development due to its good performance in object recognition. One of the crucial components in CNN is the learning mechanism of weight parameters through backpropagation. In this paper, stochastic diagonal Approximate Greatest Descent (SDAGD) is proposed to train weight parameters in CNN. SDAGD adopts...
Stochastic Diagonal Approximate Greatest Descent (SDAGD) is proposed to manage the optimization in two stages, (a) apply a radial boundary to estimate step length when the weights are far from solution, (b) apply Newton method when the weights are within the solution level set. This is inspired by a multi-stage decision control system where different strategies is used at different conditions. In...
We present an optimization technique for general object detection and an algorithm for training decision trees. By delaying the calculation of the features as late as possible we drastically reduce the execution time. At detection we alternate between evaluating the necessary features and eliminating candidates. This enables us to have both a rich pool of features and a powerful classifier while keeping...
In this paper, a method of deep learning is built to reduce the needed time on performance analyze and optimization of permanent magnet synchronous motor (PMSM). The analysis of the electromagnetic speed, torque and efficiency of PMSM is carried on with Finite Element Method (FEM), which is 8 pole-pairs, 48 stator slots and 195mm of stator external diameter. FEM model of PMSM is established, and the...
This paper presents a trajectory generation mechanism based on machine learning for a network of unmanned aerial vehicles (UAVs). For delay compensation, we apply an online regression technique to learn a pattern of network-induced effects on UAV maneuvers. Due to online learning, the control system not only adapts to changes to the environment, but also maintains a fixed amount of training data....
Modeling preference time in triathlons means predicting the intermediate times of particular sports disciplines by a given overall finish time in a specific triathlon course for the athlete with the known personal best result. This is a hard task for athletes and sport trainers due to a lot of different factors that need to be taken into account, e.g., athlete's abilities, health, mental preparations...
This paper studies the simultaneous fault diagnosis of the main reducer in the automobile transmission system assembly based on vibration signals. A simultaneous fault diagnosis model based on Paired Relevance Vector Machine (Paired-RVM) is proposed for the simultaneous fault of the main reducer, and each binary sub-classifier is trained with single fault samples and then fused by a pairing strategy...
In video surveillance, face recognition (FR) systems seek to detect individuals of interest appearing over a distributed network of cameras. Still-to-video FR systems match faces captured in videos under challenging conditions against facial models, often designed using one reference still per individual. Although CNNs can achieve among the highest levels of accuracy in many real-world FR applications,...
Compressed sensing is a signal acquisition scheme that measures signals at sub-Nyquist rate amenable to sparse recovery, with high probability, from a reduced set of measurements. One of the main requirements of compressive sensing is the sparsity of the class of signals of interest in some basis. A method to construct a sparsifying basis for a class of signals using information theoretic measures...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.