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

Abstract The aim of this study is preparing an intellectual map according to the feedback (verbally and writhingly ) in order to learn some skills of floor exercises in the women's artistic gymnastics , In addition to that the aim of this study defines on the impacts of intellectual map according to the feedback approach, and to identify the best group between the three groups study in the learning of skills approach in this study, the researchers used the experimental method, the subject of the study included on students second class in physical education and sport sciences , Baghdad University (2014-2015) , and divided into three groups for teaching skills which was under studied .The species used the specific manner by lot for selection

This research aims to examine the effectiveness of a teaching strategy based on the cognitive model of Daniel in the development of achievement and the motivation of learning the school mathematics among the third intermediate grade students in the light of their study of "Systems of Linear Equations”. The research was conducted in the first semester (1439/1440AH), at Saeed Ibn Almosaieb Intermediate School, in Arar, Saudi Arabia. A quasi-experimental design has been used. In addition, a (pre & post) achievement test (20 Questions) and a (pre & post) scale of learning motivation to the school mathematics (25 Items) have been applied on two groups: a control group (31Students), and an experimental group (29 Students). The resear

Abstract

The study aims to build a training program based on the Connectivism Theory to develop e-learning competencies for Islamic education teachers in the Governorate of Dhofar, as well as to identify its effectiveness. The study sample consisted of (30) Islamic education teachers to implement the training program, they were randomly selected. The study used the descriptive approach to determine the electronic competencies and build the training program, and the quasi-experimental approach to determine the effectiveness of the program. The study tools were the cognitive achievement test and the observation card, which were applied before and after. The study found that the effectiveness of the training program

The study aims at investigating the effectiveness of the Virtual Library Technology, in developing the achievement of the English Language Skills in the Center of Development and Continuous Education, in comparison with the individual learning via personal computer to investigate the students' attitude towards the use of both approaches. The population of the study includes the participants in the English Language course arranged in the Center. The sample includes 60 students who were randomly chosen from the whole population (participants in English Courses for the year 2009-2010). The sample is randomly chosen and divided into two experimental groups. The first group has learned through classroom technology; while the other group has l

The intelligent buildings provided various incentives to get highly inefficient energy-saving caused by the non-stationary building environments. In the presence of such dynamic excitation with higher levels of nonlinearity and coupling effect of temperature and humidity, the HVAC system transitions from underdamped to overdamped indoor conditions. This led to the promotion of highly inefficient energy use and fluctuating indoor thermal comfort. To address these concerns, this study develops a novel framework based on deep clustering of lagrangian trajectories for multi-task learning (DCLTML) and adding a pre-cooling coil in the air handling unit (AHU) to alleviate a coupling issue. The proposed DCLTML exhibits great overall control and is