• Corpus ID: 12512355

Artificial Neural Network : A Brief Overview

  title={Artificial Neural Network : A Brief Overview},
  author={Magdi Zakaria and Mabrouka Amhamed Al-Shebany and Shahenda Sarhan},
Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. Neural networks, have remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. A trained… 

Figures from this paper

Artificial Neural Network: Understanding the Basic Concepts without Mathematics
The purpose of this review is to explain the fundamental concepts of artificial neural networks.
Comparison of Artificial Neural Network and Box- Jenkins Models to Predict the Number of Patients with Hypertension in Kalar
Analysis of the monthly hypertension in Kalar by applying an autoregressive –integrated- moving average model and artificial neural networks and choosing the best and most efficient model is concluded that the prediction for patients with hypertension by using artificial neural network model is the best.
Visual learning as Object Recognition to Recognize Image for Mental Disorder Children
This application is proposing an application that will help to educate mental disorder children through the use of object recognition in visual learning and will have built-in features such as vocalize the object’s name, which will helpmental disorder children to know and remember how it is pronounced.
Neural Network-Based Automated Assessment of Fatigue Damage in Mechanical Structures
This paper proposes a methodology for automated assessment of fatigue damage, which has been tested and validated with polycrystalline-alloy specimens on an experimental apparatus and is found to be capable of detecting fatigue-damage in mechanical structures.
Optimizing Recommendations for Clustering Algorithms Using Meta-Learning
This study will use a process called meta-learning to evaluate and analyze datasets and extract a series of meta-features that can be used to intelligently recommend an optimal clustering algorithm without the cost of having to manually run the algorithm.
Arabic Handwritten Word Recognition Based on Stationary Wavelet Transform Technique using Machine Learning
The suggested SWT-WRS overcomes the lack of translation invariance in the DWT method by eliminating the up-and-down samplers from the proposed machine learning method.
Indonesian Journal of Electrical Engineering and Computer Science
The neural transliteration model in this work is based on a sequence-to-sequence neural network that is composed of two major components, an encoder that transforms source language words into a meaningful representation and the decoder that is responsible for decoding the target language words.
A Holistic Model for Recognition of Handwritten Arabic Text Based on the Local Binary Pattern Technique
A multi-stage offline holistic handwritten Arabic text recognition model using the Local Binary Pattern (LBP) technique and two machine-learning approaches; Support Vector Machines (SVM) and Artificial Neural Network (ANN).
Determination of the Groundwater Yield of horizontal wells using an artificial neural network model incorporating riverside groundwater level data
Recently, concern has arisen regarding the lowering of groundwater levels in the hinterland caused by the development of high-capacity radial collector wells in riverbank filtration areas. In this
Weather Forecasting Uses Backpropagation Algorithm Artificial Neural Network Model for Agricultural Planning in Three Villages at Three Sub-Districts of Gowa Regency
Weather is a condition of air in a narrow place, which is a condition based on symptoms of temperature, air pressure, humidity, wind, rainfall, sun exposure, cloud conditions, wind speed and others.


Multi-column deep neural networks for image classification
On the very competitive MNIST handwriting benchmark, this method is the first to achieve near-human performance and improves the state-of-the-art on a plethora of common image classification benchmarks.
Artificial neural networks in medical diagnosis
The philosophy, capabilities, and limitations of artificial neural networks in medical diagnosis through selected examples are reviewed and discussed.
Classification by ensembles of neural networks
We introduce a new procedure for training of artificial neural networks by using the approximation of an objective function by arithmetic mean of an ensemble of selected randomly generated neural
This paper focuses on IRIS plant classification using Neural Network, and Multilayer feed- forward networks are trained using back propagation learning algorithm.
Modular neural networks for multi-class object recognition
  • Yuhua Zheng, Y. Meng
  • Computer Science
    2011 IEEE International Conference on Robotics and Automation
  • 2011
A new approach consisting of a number of modular neural networks is proposed to recognize multiple classes of objects for a robotic system and the efficiencies of the proposed approach and the corresponding training strategies are demonstrated.
Two Neural Network techniques for the classification of the magnetic resonance human brain images are presented and two classifiers primarily based on supervised machine learning have been developed.
Pattern Recognition in Neural Networks with Competing Dynamics: Coexistence of Fixed-Point and Cyclic Attractors
This analysis reveals that, when associative memory is dominant, smooth transitions appear between high correlated regions and spurious states, and when sequential pattern recognition is stronger than associatives memory, the transitions are always discontinuous.
Combining of Image Classification With Probabilistic Neural Network (PNN) Approaches Based on Expectation Maximum (EM)
Based on experimental results on two test areas, it can be shown that the average accuracy rate PNN classifier is better than the Back Propagation (BP), and the Expectation Maximum (EM) increase the ability of classifiers.
Content-based image classification using a neural network