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.
In this work, we exploit a novel algorithm for capturing the Lie group manifold structure of the visual impression. By developing the single-layer Lie group model, we show how the representation learning algorithm can be stacked to yield a deep architecture. In addition, we design a Lie group based gradient descent algorithm to solve the learning problem of network weights. We show that our proposed...
This paper presents a knee torque estimation in non-pathological gait cycle at stance phase. Comparative modelling by using dynamics model and neural network model is discussed. Dynamics modelling is constructed by using simple two degree of freedom dynamics with Newtonian calculation approach and more complex four degree of freedom dynamics with Lagrangian calculation approach. Neural network based...
Recent meta-learning approaches are oriented towards algorithm selection, optimization or recommendation of existing algorithms. In this paper we show how Inductive algorithms constructed from building blocks on small data sub-sample can be scaled up to model large data sets. We demonstrate how one particular template (simple ensemble of fast sigmoidal regression models) outperforms state-of-the-art...
The architecture of educational and methodical complex for students with special needs is made by data space. The practical significance of computerized educational and methodological complex “Electrical Engineering and Electronics” is to create a modern information security training specialists training European level in the fields of electrical engineering and electronics involved in the process...
In this paper, we consider parameter estimation in latent, spatiotemporal Gaussian processes using particle Markov chain Monte Carlo methods. In particular, we use spectral decomposition of the covariance function to obtain a high-dimensional state-space representation of the Gaussian processes, which is assumed to be observed through a nonlinear non-Gaussian likelihood. We develop a Rao-Blackwellized...
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...
With the incredible growth of OSNs (online social networks), users have numerous choices every moment. However, due to the limit of time and resources, only a small part of OSNs are chosen to remain social and active by users. The dynamic changes of users' interests entail user migration. Understanding user migration behavior is important to improve business intelligence and retain users. In this...
Generative Adversarial Networks (GANs) are efficient frameworks for estimating generative model via adversarial process. However, GAN has known for suffering from training instability. Wasserstein GAN (WGAN) improves the training stability significantly but also brings an additional Lipschitz requirement for the critic network. To enforce the Lipschitz constraint, instead of weight clipping strategy,...
Area V5 or Middle Temporal (MT) area of the primate brain is said to be involved in visual motion perception. Physiological studies indicate that the neurons in MT respond selectively to the direction of moving stimuli. However in response to the complex stimuli containing multiple oriented components, a set of MT neurons are selective to the direction of the component motion whereas the other set...
This objective of this paper is to propose and evaluate a new algorithm to increase the computation and storage efficiency and to reduce the bandwidth requirements of the Wi-Fi received signal strength indicator (RSSI) maps based on Gaussian Process (GP) models. GP models are non-parametric models that estimate the likelihood function of the target variable, in this case the Wi-Fi RSSI values, conditioned...
Patient admitted with acute decompensated heart failure (ADHF) facing with high risk of mortality where 30 day mortality rates are reaching 10%. Identifying patient with high and low risk of mortality could improve clinical outcomes and hospital resources allocation. This paper proposed the use of artificial neural network to predict mortality for the patient admitted with ADHF. Results show that...
The Cerebellar Model Articulation Controller (CMAC) is a type of neural network particularly suited to real-time control applications due to fast adaptation and the ability to handle many inputs. However, the CMAC is well-known to exhibit weight (adaptive-parameter) drift when used in adaptive control, and overlearning when applied in static learning situations. A weight smoothing algorithm originally...
Recurrent neural networks with various types of hidden units have been used to solve a diverse range of problems involving sequence data. Two of the most recent proposals, gated recurrent units (GRU) and minimal gated units (MGU), have shown comparable promising results on example public datasets. In this paper, we introduce three model variants of the minimal gated unit which further simplify that...
Recently convolutional neural networks (CNNs) have essentially reached the state-of-the-art accuracies in image classification and recognition. CNNs are usually deployed in server side or cloud to handle tasks collected from mobile devices, such as smartphones, wearable devices, unmanned systems and so on. However, significant data transmission overhead and privacy issues have made it necessary to...
Text-to-speech (TTS) systems are often used as part of the user interface in wearable devices. Due to limited memory and computational/battery power in wearable devices, it could be useful to have a TTS system which requires less memory and is less computationally intensive. Conventional speech synthesis systems has separate modeling for pitch (FO-model) and spectral representation, namely Mel generalized...
Previous models based on Deep Convolutional Neural Networks (DCNN) for face verification focused on learning face representations. The face features extracted from the models are applied to additional metric learning to improve a verification accuracy. The models extract high-dimensional face features to solve a multi-class classification. This results in a dependency of a model on specific training...
In this paper, we present artificial neural network (ANN) models to predict hard and soft-responses of three configurations of arbiter based physical unclonable functions (PUFs): standard, feed-forward (FF) and modified feed-forward (MFF). The models are trained using data extracted from 32-stage arbiter PUF circuits fabricated using IBM 32 nm HKMG process. The contributions of this paper are two-fold...
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...
The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNNs) by retaining the structure and systematically reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while reducing the computational expense...
The information revolution is witnessing a rapid development in various fields that have facilitated many of the needs that meet the requirements of modern life in all aspects of service and education, as this technology has become accessible to all and has become a platform for science and an environment suitable for education and training. One of the aspects of this technology is distance education,...
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.