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.
Due to increased demand for computational efficiency for the training, validation and testing of artificial neural networks, many open source software frameworks have emerged. Almost exclusively GPU programming model of choice in such software frameworks is CUDA. Symptomatic is also lack of the support for complex-valued neural networks. With our research going exactly in that direction, we developed...
Today, machine learning based on neural networks has become mainstream, in many application domains. A small subset of machine learning algorithms, called Convolutional Neural Networks (CNN), are considered as state-ofthe- art for many applications (e.g. video/audio classification). The main challenge in implementing the CNNs, in embedded systems, is their large computation, memory, and bandwidth...
Reliable traffic light detection and classification is crucial for automated driving in urban environments. Currently, there are no systems that can reliably perceive traffic lights in real-time, without map-based information, and in sufficient distances needed for smooth urban driving. We propose a complete system consisting of a traffic light detector, tracker, and classifier based on deep learning,...
In order to improve the accuracy of Indoor Human Activity Recognition based on the spatial location information, we proposed a recognition method using the convolutional neural network(CNN). We pre-process the raw spatial location data and transfer them into motion feature, frequency feature and statistic feature. These features are input into the CNN to do local feature analysis. After that, we got...
As the analytic tools become more powerful, and more data are generated on a daily basis, the issue of data privacy arises. This leads to the study of the design of privacy-preserving machine learning algorithms. Given two objectives, namely, utility maximization and privacy-loss minimization, this work is based on two previously non-intersecting regimes — Compressive Privacy and multi-kernel method...
This paper presents a simulated memristor crossbar based Convolutional Neural Network (CNN). Deep networks implemented on GPU clusters have become the state of the art in providing excellent classification ability, at the cost of a more complex data manipulation process. In this work we show that once deep networks are trained, the analog crossbar circuits in this paper can parallelize the recognition...
This paper firstly analyzes the shortcoming of a self-organizing incremental neural network (SOINN), then proposes a novel online similarity metric and online adaptive kernel density estimator to handle 2 basic problems of unsupervised learning: clustering and density estimation. Our approach is an extension of the standard Gaussian process, online density estimator and SOINN; not only does it fully...
Recent years have seen a growing interest in neural networks whose hidden-layer weights are randomly selected, such as Extreme Learning Machines (ELMs). These models are motivated by their ease of development, high computational learning speed and relatively good results. Alternatively, constructive models that select the hidden-layer weights as a subset of the data have shown superior performance...
Deep neural networks are frequently used for computer vision, speech recognition and text processing. The reason is their ability to regress highly nonlinear functions. We present an end-to-end controller for steering autonomous vehicles based on a convolutional neural network (CNN). The deployed framework does not require explicit hand-engineered algorithms for lane detection, object detection or...
Extreme learning machine, which has recently lead to gain popularity of single hidden layer feed-forward neural networks, provides a key solution for non-linear problems with least norm and least square solutions at a very low run time. In this work, it is intended to increase the success of hyperspectral image classification with using kernel extreme learning machine. For this purpose, a hybrid kernel...
We introduce FxpNet, a framework to train deep convolutional neural networks with low bit-width arithmetics in both forward pass and backward pass. During training FxpNet further reduces the bit-width of stored parameters (also known as primal parameters) by adaptively updating their fixed-point formats. These primal parameters are usually represented in the full resolution of floating-point values...
In recent years, clasification with hyperspectral images is becoming very popular. Development of camera technology is increasing number of researchers who work in this area. Thanks to hyperspectral imaging technology, specific spectral signatures of objects can be handled. Especially, vegetation clasification is possible by using the spectral information of hyperspectral images. However due to the...
Growing concerns about increasing world population and limited food resources have been leading researchers to utilize advanced computing technology to improve the efficiency of agricultural fields. Computing technology is expected to increase the productivity, contribute to a better understanding of the relationship between environmental factors and healthy crops, reduce the labor costs for farmers...
In this paper, convolutional neural networks (CNN)-based aerial target recognition is studied by exploiting the targets' micro-Doppler profiles. In order to simulate the targets' scatterings accurately, their realistic computer-aided design (CAD) models are considered. Scattering characteristics of the targets are taken into account for a variety of radar aspects and propeller or blade rotation speeds...
In this paper, a novel feature extraction method based on t-distributed stochastic neighbor embedding (t-SNE) is presented for target recognition in synthetic aperture radar (SAR) images. It aims to search and preserve the local structure characteristic of SAR images. Recently, t-SNE has been widely studied in finding the underlying structure of data as an efficient technique. However, less attention...
Magnetic shape memory alloys (MSMA), which are a class of innovative functional materials and possess a large strain and high response frequency, are used as the actuators to be applied widely in high-precision positioning [1], such as optical alignments, diamond turning machines and scanning probe microscopy [2].
Convolutional neural networks (CNNs) have recently broken many performance records in image recognition and object detection problems. The success of CNNs, to a great extent, is enabled by the fast scaling-up of the networks that learn from a huge volume of data. The deployment of big CNN models can be both computation-intensive and memory-intensive, leaving severe challenges to hardware implementations...
Diabet is one of the metabolic trouble which is generally occurs genetic and environmental components. It happens increasing of blood level. In this study, diabet illness has been diagnosed with its features by classification with support vector machines (SVM) and artificial neural networks (multi layer perceptron). The method used for diagnosis is aritificial neural networks multi layer perceptron...
Sparsity in the weights of deep convolutional networks presents a tremendous opportunity to reduce computational requirements. In order to optimize flow of traffic systems, any viable solution must be able to operate at real-time. Existing computation frameworks do not yet realize the full potential speedup afforded by sparse neural networks. Meanwhile, the power consumption for a GPU is too great...
Kernel function implicitly maps data from its original space to a higher dimensional feature space. Kernel based machine learning algorithms are typically applied to data that is not linearly separable in its original space. Although kernel methods are among the most elegant part of machine learning, it is challenging for users to define or select a proper kernel function with optimized parameter...
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.