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

<p>In combinatorial testing development, the fabrication of covering arrays is the key challenge by the multiple aspects that influence it. A wide range of combinatorial problems can be solved using metaheuristic and greedy techniques. Combining the greedy technique utilizing a metaheuristic search technique like hill climbing (HC), can produce feasible results for combinatorial tests. Methods based on metaheuristics are used to deal with tuples that may be left after redundancy using greedy strategies; then the result utilization is assured to be near-optimal using a metaheuristic algorithm. As a result, the use of both greedy and HC algorithms in a single test generation system is a good candidate if constructed correctly. T

One of the recent significant but challenging research studies in computational biology and bioinformatics is to unveil protein complexes from protein-protein interaction networks (PPINs). However, the development of a reliable algorithm to detect more complexes with high quality is still ongoing in many studies. The main contribution of this paper is to improve the effectiveness of the well-known modularity density ( ) model when used as a single objective optimization function in the framework of the canonical evolutionary algorithm (EA). To this end, the design of the EA is modified with a gene ontology-based mutation operator, where the aim is to make a positive collaboration between the modularity density model and the proposed

The study was conducted at the fields of the Department of Horticulture and Landscape Gardening,College of Agriculture, University of Baghdad during the growing seasons of 2013- 2014 .forPerformance of Evaluation Vegetative growth and yield traits and estimate some important geneticparameter on seven selected breed of tomato which (S1-S7 ) Pure line. the results found significantdifferences between breeds in all study trails except clusters flowering number .S1 significantly plantlength which reached 227.3 .Also S1,S2 and S4 were significantly increased the number fruit for plant,Fruit weight Increased in S3 ,S6 and plant yield. Increased in S1, S4 ,S5. Genetic variation valueswere low in Floral clusters , TSS and fruit firmest and medium i

THE PROBLEM OF TRANSLATING METAPHOR IN AN ARTISTIC TEXT (ON THE MATERIAL OF RUSSIAN AND ARABIC LANGUAGES)

Aims to find out the (Extent of mathematics teachers' appreciation of the mathematical problem `multiple solutions) Research sample consisted of (100) mathematics teachers distributed on the General Directorates of Education in Baghdad (Rusafa 1/2/3) and (Karkh 1/2/ 3) There was two research approach which are: The first - two different answers of students to the same issue where teachers must assess each answer and explain which one the teacher will accept and why? The second - Different solutions of students' to the same issue, including wrong answers , Teachers should correct the answers and give them final grades (0-10). Descriptive and analytical Approch was used in this research methodology And zero hypotheses, which are as f

   In this paper we introduce many different Methods of ridge regression to solve multicollinearity problem in linear regression model. These Methods include two types of ordinary ridge regression (ORR1), (ORR2) according to the choice of ridge parameter as well as generalized ridge regression (GRR). These methods were applied on a dataset suffers from a high degree of multicollinearity, then according to the criterion of mean square error (MSE) and coefficient of determination (R2) it was found that (GRR) method performs better than the other two methods.
 

The researcher studied transportation problem because it's great importance in the country's economy. This paper which ware studied several ways to find a solution closely to the optimization, has applied these methods to the practical reality by taking one oil derivatives which is benzene product, where the first purpose of this study is, how we can reduce the total costs of transportation for product of petrol from warehouses in the province of Baghdad, to some stations in the Karsh district and Rusafa in the same province. Secondly, how can we address the Domandes of each station by required quantity which is depending on absorptive capacity of the warehouses (quantities supply), And through r