Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DiscoDVT, a discourse-aware
discrete variational Transformer to tackle the incoherence issue. DiscoDVT learns a discrete variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. To further embed discourse-aware information into the discrete latent representations, we introduce an auxiliary objective to model the discourse relations within the text. We conduct extensive experiments on two open story generation datasets and demonstrate that the latent codes learn meaningful correspondence to the discourse structures that guide the model to generate long texts with better long-range coherence.
Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account. We construct a sequential neural variational autoencode
r, which uses Gumbel-Softmax reparametrization within a carefully defined encoder, to allow for successful backpropagation during training. The core idea is to allow semi-supervised external discrete knowledge to guide, but not restrict, the variational latent parameters during training. Our experiments indicate that our approach not only outperforms multiple baselines and the state-of-the-art in narrative script induction, but also converges more quickly.
We present in this paper the neutrosophic randomized variables,
which are a generalization of the classical random variables
obtained from the application of the neutrosophic logic (a new nonclassical
logic which was founded by the American philos
opher and
mathematical Florentin Smarandache, which he introduced as a
generalization of fuzzy logic especially the intuitionistic fuzzy logic )
on classical random variables.
We present in this article a game of chance (Saint Petersburg Paradox) and
generalize it on a probability space as an example of a previsible (predictable) process,
from which we get a discrete stochastic integration (DSI). Then we define a marting
ale
and present it as a good integrator of a discrete stochastic integration ∫ , which is
called the martingale transform of by such that is a previsible process.
After that we present the most important properties of the DSI, which include that the
DSI is also a martingale , the theorem of stability for it, the definition of the covariation of
two given martingales and the proof that the DSI is centered with a specific given variance.
Finally, we define Doob-decomposition and the quadratic variation and present Itȏformula
as a certain sort of it.
The evaluation of surface water resources is a necessary input to solving water
management problems, which includes finding a relationship between precipitation and
runoff, and this relationship is a high degree of complexity. The rain of the most
important
factors that greatly effect on rivers discharge, and process to prediction of these flows must
take this factor into account, and much of the attention and study, artificial neural networks
and is considered one of the most modern methods in terms of accuracy results in linking
these multiple factors and highly complex. In order to predict the runoff contained daily to
Lake Dam Tishreen 16 in Latakia, the subject of our research, the application of different
models of artificial neural networks (ANN), was the previous input flows and rain.
Divided the data set for the period between (2006-2012) into two sets: training and
test, has been processing the data before using them as inputs to the neural network using
Discrete Wavelet Transform technique, to get rid of the maximum values and the values of
zero, where t the analysis of time series at three levels of accuracy before they are used
sub- series resulting as inputs to the Feed Forward ANN that depend back-propagation
algorithm for training.
The results indicated that with the structural neural network (1-2-6) Wavelet-ANN
model, are the best in the representation of the characteristics studied and best able to
predict runoff daily contained to Lake Dam Tishreen 16 for a day in advance, where he
reached the correlation coefficient the root of the mean of squared-errors (R2 = 0.96,
RMSE = 1.97m3 / sec), respectively.
Epilepsy is a chronic neurological disorder that occurs in the brain،
and affects approximately 2% of people around the world، where
epilepsy patients face a lot of difficulties in everyday life due to the
occurrence of seizures. Electroencephalog
ram (EEG) is used in
the automated detection of epileptic seizures، which has
Characteristics of non-linear and non-stationary. In this research،
we conducted automated detection of the seizures from the scalp
EEG signals using a Level 5 Discrete Wavelet Transforms DWT to
analyze the signal and extracting statistical features (maximum،
minimum، mean، average ، standard deviation، the ratio between
the mean values) and Categorizing using artificial neural networks
ANN for classification. The suggested detection method has
89.85% detection accuracy with 90.60% sensitivity ، and 89.1%
specificity.
Weather forecasting (especially rainfall) is one of the most important and challenging
operational tasks carried out by meteorological services all over the world. Itis furthermore
a complicated procedure that requires multiple specialized fields o
f expertise.
In this paper, a model based on artificial neural networks (ANNs) and wavelet Transform
is proposed as tool to predict consecutive monthly rainfalls (1933-2009) taken of
Homs Meteorological Station on accounts of the preceding events of rainfall data.
The feed-forward neural network with back-propagation Algorithm is used in the
learning and forecasting, where the time series of rain that detailed transactions and the
approximate three levels of analysis using a Discrete wavelet transform (DWT).
The study found that the neural network WNN structured )5-8-8-8-1(, able to predict
the monthly rainfall in Homs station on the long-term correlation of determination and root
mean squared-errors (0.98, 7.74mm), respectively.
Wavelet Transform technique provides a useful feature based on the analysis of the
data, which improves the performance of the model and applied this technique in ANNmodels
for rain because it is simple, as this technique can be applied to other models.
In this paper, we review related literature
and introduce a new general purpose simulation engine for
distributed discrete event simulation. We implemented optimized
loop CMB algorithms as a conservative algorithm in Akka
framework. The new engin
e is evaluated in terms of performance
and the ability of modeling and simulating discrete systems such
as digital circuits and single server queuing system.
The sound is an essential component of multimedia, and due to the needto be used in
many life applications such as television broadcasting andcommunication programs, so it
was necessary for the existence of audio signal processing techniquessuch as
compressing,
improving, and noisereduction.
Data compression process aims to reduce the bit rate used, by doing encoding
information using fewer bits than the original representation for transmitting and storing.
By this process,the unnecessary information is determined and removed, that means it
gives the compressed information for useable compression, which we need as a
fundamental, not the minutest details.
This research aims to study how to process sound and musical signal. It's a process
that consists of a wide range of applications like coding and digital compression for the
effective transport and storage on mobile phones and portable music players, modeling and
reproduction of the sound of musical instruments and music halls and the harmonics of
digital music, editing digital music, and classification of music content, and other things.
A digital watermark is a signal that is embedded into digital data
(text, image, audio, video) in a manner that allows it to be extracted
later. This is done by embedding a pattern which contains the
author's data into the digital data.
In this r
esearch, we propose a comparison between three types of
transformations for embedding a watermark in the frequency
domain into digital images in an efficient and secure method that
allows the watermarking any type of digital images with good
perceptibility.
