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 research aims to prepare exercises of varying resistances and muscular work exchange for 200m freestyle swimmers, in addition to these exercises’ effects on physical adequacy and the time needed to complete this distance. The experimental method is the basis for the design of the experimental group and the control group of a 100% intentionally chosen sample from a community of  elite-youth swimmers of 200m freestyle swimming for the sport season of 2020-2021 at the Police Sports Club. The sample consists of 15 swimmers that were divided, randomly, into two groups; 7 of them in the experimental group while 8 were in the control group. Physical adequacy was calculated with the use of swimmers’ mechanical energy measurements

Recently, there has been an increasing advancement in the communications technology, and due to the increment in using the cellphone applications in the diverse aspects of life, it became possible to automate home appliances, which is the desired goal from residences worldwide, since that provides lots of comfort by knowing that their appliances are working in their highest effi ciency whenever it is required without their knowledge, and it also allows them to control the devices when they are away from home, including turning them on or off whenever required. The design and implementation of this system is carried out by using the Global System of Mobile communications (GSM) technique to control the home appliances – In this work, an ele

This paper proposes improving the structure of the neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm n