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 aim of this research is to use robust technique by trimming, as the analysis of maximum likelihood (ML) often fails in the case of outliers in the studied phenomenon. Where the (MLE) will lose its advantages because of the bad influence caused by the Outliers. In order to address this problem, new statistical methods have been developed so as not to be affected by the outliers. These methods have robustness or resistance. Therefore, maximum trimmed likelihood: (MTL) is a good alternative to achieve more results. Acceptability and analogies, but weights can be used to increase the efficiency of the resulting capacities and to increase the strength of the estimate using the maximum weighted trimmed likelihood (MWTL). In order to perform t

In thisˑ paperˑ, we apply the notion ofˑ intuitionisticˑ fuzzyˑ n-fold KU-ideal of KU-algebra. Some types of ideals such as intuitionistic fuzzy KU-ideal, intuitionisticˑ fuzzy closed idealˑ and intuitionistic fuzzy n-fold KU-ideal are studied. Also, the relations between intuitionistic fuzzy n-fold KU-ideal and intuitionistic fuzzy KU-ideal are discussed. Furthermore, aˑ fewˑ results of intuitionisticˑ fuzzyˑ n-ˑfold KU-ideals of a KU-algebra underˑ homomorphismˑ are discussed.

This paper introduces the concept of fuzzy σ-ring as a generalization of fuzzy σ-algebra and basic properties; examples of this concept have been given.  As the first result, it has been proved that every  σ-algebra over a fuzzy set x*  is a  fuzzy σ-ring-over a fuzzy set x*  and construct their converse by example. Furthermore, the fuzzy ring  concept has been studied to generalize fuzzy algebra and its relation. Investigating  that the concept of fuzzy  σ-Ring is a stronger form of a fuzzy ring  that is every fuzzy σ-Ring over a fuzzy set x* is a fuzzy ring over a fuzzy set x* and construct their converse by example. In addition, the idea of the smallest, as an important property in the study of real analysis, is studied

In this paper, we apply the notion of a bipolar fuzzy n-fold KU-ideal of KU- algebras. We introduce the concept of a bipolar fuzzy n-fold KU-ideal and investigate several properties. Also, we give relations between a bipolar fuzzy n- fold KU-ideal and n-fold KU-ideal. The image and the pre-image of bipolar fuzzy n-fold KU-ideals in KU-algebras are defined and how the image and the pre- image of bipolar fuzzy n-fold KU-ideals in KU-algebras become bipolar fuzzy n- fold KU-ideals are studied. Moreover, the product of bipolar fuzzy n-fold KU- ideals in Cartesian product KU-algebras is given.

Statistical learning theory serves as the foundational bedrock of Machine learning (ML), which in turn represents the backbone of artificial intelligence, ushering in innovative solutions for real-world challenges. Its origins can be linked to the point where statistics and the field of computing meet, evolving into a distinct scientific discipline. Machine learning can be distinguished by its fundamental branches, encompassing supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Within this tapestry, supervised learning takes center stage, divided in two fundamental forms: classification and regression. Regression is tailored for continuous outcomes, while classification specializes in c

A field experiment was conducted at botanical garden of Department of Biology, College of Education for Pure Science (Ibn Al-Haitham), University of Baghdad, during the growth winter season of 2016-2017 to study the effect of different concentrations (0, 10, 20) mg.L^-1 of abscisic acid and (0, 50, 100, 150) mg.L^-1 of vitamin C and their interaction on some plant hormones of pea plant (Pisum sativum L.). The results showed that ABA 20 mg.L^-1 decreased IAA about 27.44%, GA₃ about 19.73% and Kinetin 15.37% while vitamin C with 150 mg.L^-1 increased IAA 27.43%, GA₃ 45.31% and Kinetin 58.53%, but ABA increased about 23.01% for ABA and 34.93% for vitamin C compared with

Background: Measuring the concentration of hepatitis B surface antigen (HbsAg) in HBV patients can be determined with immunoassay techniques. This study aimed to measure the HbsAg titers in chronic HBV patients and to assess its correlation with patients' ages, gender, and with the levels of liver enzymes and total serum bilirubin. Materials and Method: Fifty-eight chronic hepatitis B infected patients were enrolled in this study. Age and gender of the patients were recorded. HbsAg concentration was tested with automated Immunoanalyzer. The patients were also tested for ALT, AST, ALP, and TSB by automated chemistry analyzer. Results: All the chronic HBV patients have positive HBsAg titers above the negative cutoff (0.05U/L) with mea