One of the disadvantages in Connection of wind energy conversion systems (WECSs) to transmission networks is plentiful turbulence of wind speed. Therefore effects of this problem must be controlled. owadays, pitch-controlled WECSs are increasingly used for variable speed and pitch wind turbines. Megawatt class wind turbines generally turn at variable speed in wind farm. Thus turbine operation m...

We propose a convolutional neural network as an alternative to recurrent neural networks for separating out individual speakers in a sound mixture. Our results achieve state-of-the-art results with an order of magnitude fewer parameters. We also characterize the robustness of both models to generalize to three different testing conditions including a novel dataset. We create a new dataset RealT...

In cities with tall buildings, emergency responders need an accurate floor level location to find 911 callers quickly. We introduce a system to estimate a victim’s floor level via their mobile device’s sensor data in a two-step process. First, we train a neural network to determine when a smartphone enters or exits a building via GPS signal changes. Second, we use a barometer equipped smartphon...

For every prediction we might wish to make, we must decide what to observe (what source of information) and when to observe it. Because making observations is costly, this decision must trade off the value of information against the cost of observation. Making observations (sensing) should be an active choice. To solve the problem of active sensing we develop a novel deep learning architecture:...

This thesis is concerned with normal and pathological oscillations generated in thalamocortical neuronal network. By means of anatomically and physiologically based computational models we attempt to provide insight into phenomena such as event-related dynamics of alpha band rhythms and spontaneous generation of absence seizures. We present novel hypothesis regarding the neurophysiological subs...

To improve ATMs’ cash demand forecasts, this paper advocates the prediction of cash demand for groups of ATMs with similar day-of-the week cash demand patterns. We first clustered ATM centers into ATM clusters having similar day-of-the week withdrawal patterns. To retrieve “day-of-the-week” withdrawal seasonality parameters (effect of a Monday, etc) we built a time series model for each ATMs. F...

In this letter, we describe a convergence of batch gradient method with a penalty condition term for a narration feed forward neural network called pi-sigma neural network, which employ product cells as the output units to inexplicit amalgamate the capabilities of higher-order neural networks while using a minimal number of weights and processing units. As a rule, the penalty term is condition ...

Deep networks commonly perform better than shallow ones (Krizhevsky et al., 2012; Simonyan & Zisserman, 2015; He et al., 2016), but allocating the proper amount of computation for each particular input sample remains an open problem. This issue is particularly challenging in sequential tasks, where the required complexity may vary for different tokens in the input sequence. Adaptive Computation...

This thesis broadens the space of rich yet practical models for structured prediction. Weintroduce a general framework for modeling with four ingredients: (1) latent variables,(2) structural constraints, (3) learned (neural) feature representations of the inputs, and(4) training that takes the approximations made during inference into account. The thesisbuilds up to this framewo...