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

This paper deals with constructing mixed probability distribution from mixing exponential

In this research we assumed that the number of emissions by time (𝑡) of radiation particles is distributed poisson distribution with parameter (𝑡), where  < 0 is the intensity of radiation. We conclude that the time of the first emission is distributed exponentially with parameter 𝜃, while the time of the k-th emission (𝑘 = 2,3,4, … . . ) is gamma distributed with parameters (𝑘, 𝜃), we used a real data to show that the Bayes estimator 𝜃 ∗ for 𝜃 is more efficient than 𝜃̂, the maximum likelihood estimator for 𝜃 by using the derived variances of both estimators as a statistical indicator for efficiency

This research reports an error analysis of close-range measurements from a Stonex X300 laser scanner in order to address range uncertainty behavior based on indoor experiments under fixed environmental conditions. The analysis includes procedures for estimating the precision and accuracy of the observational errors estimated from the Stonex X300 observations and conducted at intervals of 5 m within a range of 5 to 30 m. The laser 3D point cloud data of the individual scans is analyzed following a roughness analysis prior to the implementation of a Levenberg–Marquardt iterative closest points (LM-ICP) registration. This leads to identifying the level of roughness that was encountered due to the range-finder’s limitations in close

This work analyzes the effectiveness of an artificial intelligence (AI) community- building workshop designed for high school teachers and it focuses on contemporary issues related to AI concepts and applications. A group of high school teachers from local education districts attended a one-day AI hands-on workshop at our university. The workshop included several AI-related topics and hands-on examples and exercises aiming to introduce AI concepts and tools relevant to pre-college education. The participating teachers were expected to become a part of a collaborative network created to design, develop, and implement novel AI learning modules for high school students. Initial and a post-training surveys have been used to measure the

      In this research, the nonparametric technique has been presented to estimate the time-varying coefficients functions for the longitudinal balanced data that characterized by observations obtained through (n) from the independent subjects, each one of them is measured repeatedly by group of  specific time points (m). Although the measurements are independent among the different subjects; they are mostly connected within each subject and the applied techniques is the Local Linear kernel LLPK technique. To avoid the problems of dimensionality, and thick computation, the two-steps method has been used to estimate the coefficients functions by using the two former technique. Since, the two-

The problem of Multicollinearity is one of the most common problems, which deal to a large extent with the internal correlation between explanatory variables. This problem is especially Appear in economics and applied research, The problem of Multicollinearity has a negative effect on the regression model, such as oversized variance degree and estimation of parameters that are unstable when we use the Least Square Method ( OLS), Therefore, other methods were used to estimate the parameters of the negative binomial model, including the estimated Ridge Regression Method and the Liu type estimator, The negative binomial regression model is a nonline

Credit risk assessment has become an important topic in financial risk administration. Fuzzy clustering analysis has been applied in credit scoring. Gustafson-Kessel (GK) algorithm has been utilised to cluster creditworthy customers as against non-creditworthy ones. A good clustering analysis implemented by good Initial Centres of clusters should be selected. To overcome this problem of Gustafson-Kessel (GK) algorithm, we proposed a modified version of Kohonen Network (KN) algorithm to select the initial centres. Utilising similar degree between points to get similarity density, and then by means of maximum density points selecting; the modified Kohonen Network method generate clustering initial centres to get more reasonable clustering res