AbstructWe present two constructions of controllers that globally stabilize linear systems subject to control saturation. We allow essentially arbitrary saturation functions. The only conditions imposed on the system are the obvious necessary ones, namely that no eigenvalues of the uncontrolled system have positive real part and that the standard stabfiability rank condition hold. One of the co...

Tourette’s syndrome (see interactive graphic, available with the full text of this article at NEJM .org). DBS therapy is usually considered only after all other treatments have been exhausted, but becoming “bionic” has provided many patients with a new lease on life. Thanks in large part to the contributions of two extraordinary scientists, we have entered the era of human neuralnetwork modulat...

consecutive droughts in sistan and baloochestan province cause water resources restriction and this isa very significant problem for this region. in this study, in order to forecast the drought cycle in 9climatological stations in the province, we used artificial neural networks. the input data wereaverage of annual rainfall data in all stations and also deciles precipitation index, which the f...

If several mental states can be reliably distinguished by recognizing patterns in EEG, then a paralyzed person could communicate to a device like a wheelchair by composing sequencesof these mental states. In this article, we report on a study comparing four representations of EEG signals and their classification by a two-layer neural network with sigmoid activation functions. The neuralnetwork ...

Recent trends suggest that neuralnetwork-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these ...

In the recent contribution [9], it was given a unified view of four neuralnetwork-learning-based singular-value-decomposition algorithms, along with some analytical results that characterize their behavior. In the mentioned paper, no attention was paid to the specific integration of the learning equations which appear under the form of first-order matrix-type ordinary differential equations on ...

This paper considers a linear model with time varying parameters controlled by a neural network to analyze and forecast nonlinear time series.We show that this formulation, called neural coefficient smooth transition autoregressive (NCSTAR) model, is in close relation to the threshold autoregressive (TAR) model and the smooth transition autoregressive (STAR) model with the advantage of naturall...

This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slotfilling dialog systems. Our architecture is inspired by previously proposed neuralnetwork-based belief-tracking systems. In addition we extended some parts of our modular architecture with differentiable rules to allow end-to-end training. We hypothesize that these rules allow our...

We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neuralnetwork infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning framework...