A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

The electron correlation for inter-shells (1s 2p), (1s 3p) and (1s 3d) was described by the inter-particle radial distribution function f(r12). It was evaluated for Li-atom in the different excited states (1s2 2p), (1s2 3p) and (1s2 3d) using Hartree-Fock approximation (HF). The inter particle expectation values for these shells were also evaluated. The calculations were performed using Mathcad 14 program.

The Boltzmann transport equation is solved by using two- terms approximation for pure gases . This method of solution is used to calculate the electron energy distribution function and electric transport parameters were evaluated in the range of E/N varying from . 172152110./510.VcmENVcm
From the results we can conclude that the electron energy distribution function of CF4 gas is nearly Maxwellian at (1,2)Td, and when E/N increase the distribution function is non Maxwellian. Behavior of electrons transport parameters is nearly from the experimental results in references. The drift velocity of electron in carbon tetraflouride is large compared with other gases

             It is the regression analysis is the foundation stone of knowledge of statistics , which mostly depends on the ordinary least square method , but as is well known that the way the above mentioned her several conditions to operate accurately and the results can be unreliable , add to that the lack of certain conditions make it impossible to complete the work and analysis method and among those conditions are the multi-co linearity problem , and we are in the process of detected that problem between the independent variables using farrar –glauber test , in addition to the requirement linearity data and the lack of the condition last has been resorting to the

Spatial data observed on a group of areal units is common in scientific applications. The usual hierarchical approach for modeling this kind of dataset is to introduce a spatial random effect with an autoregressive prior. However, the usual Markov chain Monte Carlo scheme for this hierarchical framework requires the spatial effects to be sampled from their full conditional posteriors one-by-one resulting in poor mixing. More importantly, it makes the model computationally inefficient for datasets with large number of units. In this article, we propose a Bayesian approach that uses the spectral structure of the adjacency to construct a low-rank expansion for modeling spatial dependence. We propose a pair of computationally efficient estimati

With the proliferation of both Internet access and data traffic, recent breaches have brought into sharp focus the need for Network Intrusion Detection Systems (NIDS) to protect networks from more complex cyberattacks. To differentiate between normal network processes and possible attacks, Intrusion Detection Systems (IDS) often employ pattern recognition and data mining techniques. Network and host system intrusions, assaults, and policy violations can be automatically detected and classified by an Intrusion Detection System (IDS). Using Python Scikit-Learn the results of this study show that Machine Learning (ML) techniques like Decision Tree (DT), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) can enhance the effectiveness of an Intrusi

     This article aims to determine the time-dependent heat coefficient together with the temperature solution for a type of semi-linear time-fractional inverse source problem by applying a method based on the finite difference scheme and Tikhonov regularization. An unconditionally stable implicit finite difference scheme is used as a direct (forward) solver. While by the MATLAB routine lsqnonlin from the optimization toolbox, the inverse problem is reformulated as nonlinear least square minimization and solved efficiently. Since the problem is generally incorrect or ill-posed that means any error inclusion in the input data will produce a large error in the output data. Therefore, the Tikhonov regularization technique is applie