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.
Deep learning (DL) training-as-a-service (TaaS) is an important emerging industrial workload. TaaS must satisfy a wide range of customers who have no experience and/or resources to tune DL hyper-parameters (e.g., mini-batch size and learning rate), and meticulous tuning for each user's dataset is prohibitively expensive. Therefore, TaaS hyper-parameters must be fixed with values that are applicable...
Loop closure detection is important in simultaneous localization and mapping (SLAM) systems. In this paper, Generative Adversarial Networks (GAN), an unsupervised deep architecture is employed to detect the loop closure for vision-based SLAM systems. Instead of extracting handcrafted features like SIFT, SURF or ORB. Generative Adversarial Networks are based on image features. Similar to the task about...
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...
This paper studies the optimization of pilot training signals in Massive MIMO systems with insufficient pilot length. We aim at finding the optimal pilot design and pilot length that maximize the Spectral Efficiency (SE) of the system. To achieve that, we firstly derive an approximation of average achievable capacity, which is related to channel estimation error and pilot signals. Then some analysis...
Deep Neural Networks (DNNs) have emerged as a powerful and versatile set of techniques showing successes on challenging artificial intelligence (AI) problems. Applications in domains such as image/video processing, autonomous cars, natural language processing, speech synthesis and recognition, genomics and many others have embraced deep learning as the foundation. DNNs achieve superior accuracy for...
Deep learning with a large number of parametersrequires distributed training, where model accuracy and runtimeare two important factors to be considered. However, there hasbeen no systematic study of the tradeoff between these two factorsduring the model training process. This paper presents Rudra, aparameter server based distributed computing framework tunedfor training large-scale deep neural networks...
We have deployed a big data platform for the insurance company. One can select the data they need from database, do data analysis job and save the final model to the model pool using the platform. We completed churn prediction task on both SPSS [1] and Spark [7] using the data providing by X insurance company and carefully compared the execution flow, runtime, model evaluation, and model precision...
Improving the perceptual quality of speech signals is a key yet challenging problem for many real world applications. In this paper, we propose a perceptually motivated approach based on deep neural networks (DNNs) for speech enhancement task. The proposed approach take into consider the masking properties of the human auditory system and reduces the perceptual effect of the residual noise. Given...
We propose a method for leveraging publicly available labeled facial age datasets to estimate age from unconstrained face images at the ChaLearn Looking at People (LAP) challenge 2015 [9]. We first learn discriminative age related representation on multiple publicly available age datasets using deep Convolutional Neural Networks (CNN). Training CNN is supervised by rich binary codes, and thus modeled...
In order to achieve the fast classification for Ultra-low-frequency (ULF) electron field data in the Space, this paper designs an electric field classifier based on the back-propagation (BP) neural network with extracting the ULF section electric field waveform data of the Wenchuan earthquake, using the statistical methods to obtain four characteristics of the mean value, mean square error, skewness...
This paper proposes a novel distributed parallel EM modeling technique to speed up the process of neural network modeling for EM structures. Existing techniques for EM modeling usually need to repeatedly change the parameters of microwave devices and drive the EM simulator to obtain sufficient training and testing samples. As the complexity in EM modeling problem increases, traditional techniques...
In this paper, we explore service recommendation and selection in the reusable composition context. The goal is to aid developers finding the most appropriate services in their composition tasks. We specifically focus on mashups, a domain that increasingly targets people without sophisticated programming knowledge. We propose a probabilistic matrix factorization approach with implicit correlation...
Nowadays, as the development of mobile communication, it is very important to serve users. Because of the subjectivity of user experience, the data of user experience has deviation. In the paper, a cooperative modeling method based on the improved Support Vector Machine is proposed, which can evaluate the quality of experience by using measurement report. The results of the experiments show that our...
In recent years, extraordinary bad and bad chemical accidents caused by hazardous chemicals leak become frequent in China, but fire brigades are very short of pressure emergency leakage sealing test device and simulated training device for response. Shanghai Fire Research Institute of the Ministry of Public Security has developed a set of multi-functional pressure emergency leakage sealing test and...
Open-Loop Fiber Optic Gyroscopes (FOG) is widely used, which is easily affected by the temperature around it. Its temperature model has a very complicated nonlinear characteristic. A BP neural network model with advantage of approximating the nonlinear function was developed to simulate outputs of an open-loop FOG and then compensate the FOG's temperature error in full temperature range (−50°C∼ +70...
In this paper, we propose a Wi-Fi positioning method based on Deep Learning (DL). To deal with the variant and unpredictable wireless signals, the positioning is casted in a four-layer Deep Neural Network (DNN) structure that is capable of learning reliable features from a large set of noisy samples and avoids the need for hand-engineering. Also, to maintain the temporal coherence, a Hidden Markov...
This paper presents a real-time human action recognition method based on a modified Deep Belief Network (DBN) model. To recognize human actions, the positions of human joints are taken into account. Each action is made of a sequence of human joint positions. Since the classic DBN cannot deal with temporal information, the proposed method employs the conditional Restricted Boltzmann Machine (cRBM)...
In this paper, we propose a limited feedback based underlay spectrum sharing scheme where a secondary decode-and-forward opportunistic relay network shares the spectrum with a pair of primary users. The primary destination and each of the N secondary relays send 1-bit feedback of channel quality information to their corresponding transmitters. By overhearing the primary feedback and receiving the...
Natural disasters can lead to severe losses in human life and property. Because many factors combine in a disaster, such events are difficult to forecast accurately. A cooperative multi-classifier method is proposed in this paper to mine local area meteorological data. The proposed method is verified by the implementation of both base and integration classifiers. Experimental results indicate that...
Phased-Mission System (PMS) is a kind of typical complex systems. Most weapon systems executing battle mission and usage mission belongs to this type of complex systems. PMS and its' mission sustainability evaluation parameters included mission reliability, dependability, and mission effectiveness are given. In view of the usage characteristics of fact weapon system, some hypotheses are given for...
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.