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.
The paper exposes the behavior of the Decision Trees (DT) algorithms on a big database with many cases and many attributes: Forest Covertype (FC) from UCI Knowledge Discovery in Databases Archive. In classification experiments considered have been taken into account 22 splitting criteria and two pruning methods whose performances were presented in terms of classification error rate on test data, data...
We propose a gray coding method for deep neural network (DNN) based decoder. With multiple resources considered together, DNN can be used to decode corrupted signals. In deep learning training, stochastic gradient descent (SGD) algorithm is used, which means that the cost function must be differentiable. Then, allocating the discrete bits for each symbol is difficult. To solve this problem, the basic...
This paper presents a novel approach to launch and defend against the causative and evasion attacks on machine learning classifiers. As the preliminary step, the adversary starts with an exploratory attack based on deep learning (DL) and builds a functionally equivalent classifier by polling the online target classifier with input data and observing the returned labels. Using this inferred classifier,...
Residual network(ResNet) is an effective instance and a significant extension of deep convolutional neural network. ResNet utilizes skip-connection between input layers and output layers to solve the vanishing gradient problem. Due to the powerfulness of skip-connection, the gradient can flow directly through the identity function from later layers to the earlier layers. However, skip-connection makes...
This paper discusses how to apply the ensemble learning for the individual learners on the randomly splitting data. Rather than letting the individual learners learn independently on the different subsets, it would be better for the individual learners to learn cooperatively by exchanging the learned values. In this way, the individual learners could learn the whole given data together while they...
Randomized feed-forward artificial neural networks (ANNs) have been employed in various domains. This paper was written in order to assess the efficiency of the basic forms of randomized feed-forward ANNs, which are randomized weight artificial neural network, random vector functional link network, extreme learning machine, and radial bases function neural network. In order to compare these methods,...
This paper carries out a large dimensional analysis of the standard regularized quadratic discriminant analysis (QDA) classifier designed on the assumption that data arise from a Gaussian mixture model. The analysis relies on fundamental results from random matrix theory (RMT) when both the number of features and the cardinality of the training data within each class grow large at the same pace. Under...
Recent developments in deep learning methods have greatly influenced the performances of speech recognition systems. In a Hidden Markov model-Deep neural network (HMM-DNN) based speech recognition system, DNNs have been employed to model senones (context dependent states of HMM), where HMMs capture the temporal relations among senones. Due to the use of more deeper networks significant improvement...
Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU...
Recent work in the recognition of naturalistic expressions, which is also known as spontaneous facial expressions recognition, has attracted researchers' attention due to its importance in different behavioural and clinical applications. The main design challenges in the area of emotion computing for automatic recognition of spontaneous facial expression are the face pose, capture distance, illumination...
The article presents studies on the automatic whispery speech recognition. In the performed research a new corpus with whispery speech has been used. The aim of studies presented in this paper was to check, how the vocabulary size and the language model order influence on the speech recognition quality. It has been concluded that even using recordings with 5,000 different words only it is possible...
Intrusion detection techniques have been extensively used as a protective measure against network attacks. Machine learning (ML) has been widely recognized as an effective method for data based intrusion detection analysis. Especially, semi-supervised ML approaches apply both labelled and unlabelled data to train the detection model, which can avoid the high cost of labelling data. In this paper,...
This paper proposes a hybrid negative correlation learning in which each individual neural network in an neural network ensemble would either learn a data point by negative correlation learning or learn to be different to the neural network ensemble. The implementation is through randomly splitting the training set into two subsets for each individual neural network in learning. On one subset of the...
This paper addresses the band selection of a hyperspectral image. Considering a binary classification, we devise a method to choose the more discriminating bands for the separation of the two classes involved, by using a simple algorithm: single-layer neural network. After that, the most discriminative bands are selected, and the resulting reduced data set is used in a more powerful classifier, namely,...
Convolutional neural network (CNN) has been successfully applied in character recognition. To further reduce the error rate of classification, based on traditional CNN, a recurrent-type CNN (RCNN) is presented in this paper. The Elman-Jordan recurrent model is embedded in the full connection layer of the proposed CNN. By optimizing the structure of the traditional CNN and making full use of the better...
Nowadays the CNN is widely used in practical applications for image classification task. However the design of the CNN model is very professional work and which is very difficult for ordinary users. Besides, even for experts of CNN, to select an optimal model for specific task may still need a lot of time (to train many different models). In order to solve this problem, we proposed an automated CNN...
Kinship verification from facial images is a challenging task in computer vision. The majority of recent verification algorithms concatenate all features of patches in facial image to build the final feature representation, which implicitly takes every facial part into account for kinship verification. However, it is questionable by considering all face regions since certain facial parts such as the...
Bagging is a popular method used to increase the accuracy of classification, by training a set of classifiers on slightly different datasets and aggregating their output by voting. Usually, the majority voting is used for this purpose, or the plurality voting, when the problem has multiple class values. In this study, we analyze the influence of several voting methods on the performance of two classification...
Vehicle classification has been a challenging problem because of pose variations, weather / illumination changes, inter-class similarity and insufficient training dataset. With the help of innovative deep learning algorithms and large scale traffic surveillance dataset, we are able to achieve high performance on vehicle classification. In order to improve performance, we propose an ensemble of global...
This paper aims to introduce a new vehicle type classification scheme on the images from multi-view surveillance camera. We propose four concepts to increase the performance on the images which have various resolutions from multi-view point. The Deep Learning method is essential to multi-view point image, bagging method makes system robust, data augmentation help to grow the classification capability,...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.