Novel approaches to estimate information measures using neural networks are well-celebrated in recent years both in the information theory and machine learning communities. These neural-based estimators are shown to converge to the true values when estimating mutual information and conditional mutual information using independent samples. However, if the samples in the dataset are not independent, the consistency of these estimators requires further investigation. This is of particular interest for a more complex measure such as the directed information, which is pivotal in characterizing causality and is meaningful over time-dependent variables. The extension of the convergence proof for such cases is not trivial and demands further assumptions on the data. In this paper, we show that our neural estimator for conditional mutual information is consistent when the dataset is generated with samples of a stationary and ergodic source. In other words, we show that our information estimator using neural networks converges asymptotically to the true value with probability one. Besides universal functional approximation of neural networks, a core lemma to show the convergence is Birkhoff’s ergodic theorem. Additionally, we use the technique to estimate directed information and demonstrate the effectiveness of our approach in simulations. 相似文献
Temperature-sensitive poly(N-isopropylacrylamide) (PNIPAAm) brushes with different molecular weights M(n) and grafting densities σ were prepared by the "grafting-to" method. Changes in their physicochemical properties according to temperature were investigated with the help of in situ spectroscopic ellipsometry and in situ attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy. Brush criteria indicate a transition between a brush conformation below the lower critical solution temperature (LCST) and an intermediate to mushroom conformation above the LCST. By in situ ellipsometry distinct changes in the brush layer parameters (wet thickness, refractive index, buffer content) were observed. A broadening of the temperature region with maximum deswelling occurred with decreasing grafting density. The brush layer properties were independent of the grafting density below the LCST, but showed a virtually monotonic behavior above the LCST. The midtemperature ?(half) of the deswelling process increased with increasing grafting density. Thus grafting density-dependent design parameters for such functional films were presented. For the first time, ATR-FTIR spectroscopy was used to monitor segment density and hydrogen bonding changes of these very thin PNIPAAm brushes as a function of temperature based on significant variations of the methyl stretching, Amide I, as well as Amide II bands with respect to intensity and wavenumber position. No dependence on M(n) and σ in the wavenumber shift of these bands above the LCST was found. The temperature profile of these band intensities and thus segment density was found to be rather step-like, exceeding temperatures around the LCST, while the respective profile of their wavenumber positions suggested continuous structural and hydration processes. Remaining buffer amounts and residual intermolecular segment/water interaction in the collapsed brushes above the LCST could be confirmed by both in situ methods. 相似文献
The accurate prediction of the solar diffuse fraction (DF), sometimes called the diffuse ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse irradiance research is discussed and then three robust, machine learning (ML) models are examined using a large dataset (almost eight years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid adaptive network-based fuzzy inference system (ANFIS), a single multi-layer perceptron (MLP) and a hybrid multi-layer perceptron grey wolf optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various solar and DF irradiance data, from Spain. The results were then evaluated using frequently used evaluation criteria, the mean absolute error (MAE), mean error (ME) and the root mean square error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance in both the training and the testing procedures. 相似文献
Numerical Algorithms - In this paper, we present a new fast and deterministic algorithm for the inverse discrete cosine transform of type II that reconstructs the vector $\mathbf {x}\in \mathbb... 相似文献
2-Deoxy-D-glucopyranosyl phenylsulfones 3a–c have been synthesized in 75–83% yield from commercial tri-O-acetyl-D-glucal 1. Their reductive desulfonylation by lithium naphthalenide and reaction of the intermediate glycosyl-lithium 5 with aldehydes leads to α-D-C-glucopyranosides with high stereoselectivity. 相似文献
In this paper, at the first, new correlations were proposed to predict the rheological behavior of MWCNTs–SiO2/EG–water non-Newtonian hybrid nanofluid using different sets of experimental data for the viscosity, consistency and power law indices. Then, based on minimum prediction errors, two optimal artificial neural network models (ANNs) were considered to forecast the rheological behavior of the non-Newtonian hybrid nanofluid. One hundred and ninety-eight experimental data were employed for predicting viscosity (Model I). Two sets of forty-two experimental data also were considered to predict the consistency and power law indices (Model II). The data sets were divided to training and test sets which contained respectively 80 and 20% of data points. Comparisons between the correlations and ANN models showed that ANN models were much more accurate than proposed correlations. Moreover, it was found that the neural network is a powerful instrument in establishing the relationship between a large numbers of experimental data. Thus, this paper confirmed that the neural network is a reliable method for predicting the rheological behavior of non-Newtonian nanofluids in different models.