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.
The popularity of neural networks (NNs) spans academia [1], industry [2], and popular culture [3]. In particular, convolutional neural networks (CNNs) have been applied to many image based machine learning tasks and have yielded strong results [4]. The availability of hardware/software systems for efficient training and deployment of large and/or deep CNN models is critical for the continued success...
One of the most investigated methods to increase the accuracy of convolutional neural networks (CNN) is by increasing its depth. However, increasing the depth also increases the number of parameters, which makes convergence of back-propagation very slow and prone to overfitting. Convolutional networks with deep supervision (CNDS) add auxiliary branch to addresses the problem of slower convergence...
Large-scale deep convolutional neural networks (CNNs) are widely used in machine learning applications. While CNNs involve huge complexity, VLSI (ASIC and FPGA) chips that deliver high-density integration of computational resources are regarded as a promising platform for CNN's implementation. At massive parallelism of computational units, however, the external memory bandwidth, which is constrained...
Finding the location of a mobile user is a classical and important problem in pervasive computing, because location provides a lot of information about the situation of a person from which adaptive computer systems can be created. While the inference of location outside buildings is possible with GPS or similar satellite systems, these are unavailable inside buildings. A large number of methods has...
Hardware accelerators for convolutional neural network (CNN) accompany a large amount of SRAM in order to reduce the number of expensive off-chip DRAM accesses. This design trend gives implications to architects: the SRAM area will dominate the entire chip area for the future CNN accelerators. Since the probability of soft errors such as energetic particle strikes goes as the density of SRAM, errors...
Convolution Neural Networks today provide the best results for many image detection and image recognition problems. The network accuracy increase in the past years is obtained through an increase in complexity of the structure and amount of parameters of the deep networks. Memory bandwidth and power consumption constraints are limiting the deployment of such state-of-the-art architecture in low power...
The paper presents a comparative analysis of possibilities for assessment of the freshness of widespread foodstuffs like white brined cheese, yellow cheese, meat and bacon. The freshness is represented by the time of storage in specific conditions (dark room with temperature of 20°C). The time of storage is assessed using regression predictive models of features, related to the freshness product and...
Detection algorithms for electroencephalography (EEG) data typically employ handcrafted features that take advantage of the signal's specific properties. In the field of interictal epileptic discharge (IED) detection, the feature representation that provides optimal classification performance is still an unresolved issue. In this paper, we consider deep learning for automatic feature generation from...
The major challenge of machine learning based image steganalysis lies in obtaining powerful feature representations. Recently, Qian et al. have shown that Convolutional Neural Network (CNN) is effective for learning features automatically for steganalysis. In this paper, we follow up this new paradigm in steganalysis, and propose a framework based on transfer learning to help the training of CNN for...
Human action recognition is a challenging vision task due to the complex action patterns in the real-world videos. In this work, we propose a DeepAction Kernel Gaussian Process, which takes advantage of Gaussian process (GP) and deep learning, to capture the distinctive action characteristics. Specifically, we design a unified, deep and non-adjacent kernel structure within Gaussian process to classify...
Computer vision is widely used at present. However, fruit recognition is still a problem for the stacked fruits on weighing scale because of complexity and overlap. In this paper, a fruit recognition algorithm based on convolution neural network(CNN) is proposed. At first the image regions are extracted using selective search algorithm, then the regions have been selected by means of an entropy of...
In order to enhance the precision of biofouling estimation, this paper uses Least Squares Support Vector Machine (LSSVM) to establish a prediction model based on the estimator with radial basis function kernel. The main Influencing factors include pH, conductivity, total number of bacteria, dissolved oxygen, TN, NH3-N was selected as the input variable, Biofouling as the output variable. The results...
Application of the benefits of modern computing technology to improve the efficiency of agricultural fields is inevitable with growing concerns about increasing world population and limited food resources. Computing technology is crucial not only to industries related to food production but also to environmentalists and other related authorities. It is expected to increase the productivity, contribute...
In this paper, we demonstrate nonlinear features extracted by deep neural network have better results in the task of dictionary learning. A nonlinear dictionary learning model is constructed and the optimization algorithm is developed. In the learning algorithm, we use the deep neural network to convey raw samples to feature space and learn a nonlinear dictionary. The extensive experimental results...
The status of the insulators in power line can directly affect the reliability of the power transmission systems. Computer vision aided approaches have been widely applied in electric power systems. Inspecting the status of insulators from aerial images has been challenging due to the complex background and rapid view changing under different illumination conditions. In this paper, we propose a novel...
Multiple-kernel k-means (MKKM) clustering has demonstrated good clustering performance by combining pre-specified kernels. In this paper, we argue that deep relationships within data and the complementary information among them can improve the performance of MKKM. To illustrate this idea, we propose a diversity-induced MKKM algorithm with extreme learning machine (ELM)-based feature extracting method...
Complex robotics task such as biped walking, tennis-like swing, object grasping etc, depend on state prediction, complex motion generation and stable execution of motion command. Predictions of states get more accurate over time, hence the robot behavior need to be updated continuously. Such state updates cannot be incorporated straight forwardly in most trajectory generation solutions. dynamic movement...
This paper presents a simulated memristor crossbar implementation of a deep Convolutional Neural Network (CNN). In the past few years deep neural networks implemented on GPU clusters have become the state of the art in image classification. They provide excellent classification ability at the cost of a more complex data manipulation process. However once these systems are trained, we show that the...
In this paper, an information-theoretic-based adaptive resonance theory (IT-ART) neural network architecture is presented. Each IT-ART category is defined by the first and second order statistics (mean and covariance matrix) of the cluster or class it represents. This information is used to estimate probability density functions (multivariate Gaussians) and compute the activation functions. The match...
Through multiple levels of abstraction, deep learning takes advantage of multiple layers models to find the complicated structure and learn the high level representations of data. In recent years, deep learning has made great progress in object detection, speech recognition, and many other domains. The robustness of learning systems with deep architectures is however rarely studied and needs further...
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.