Artificial neural network is composed of interconnected units that are called neurons. The function of neuron is to collect inputs from the environment and then generate an output on the basis of the input. Between a pair of neurons is associated a numerical strength which is called the synaptic weight. Two phases are required in order to develop an artificial neural network model. The first is the learning or training phase and the second one is the testing phase. Artificial neural network is trained by providing the network with examples which is called trauzing patterns. The synaptic weights are modified to the model in the training phase so as to train the problem which may be tested in the testing phase with some new unknown parameters and patterns and then its efficiency can be checked. Depending on the nature of training artificial neural network can be categorized into supervised Artificial NN and unsupervised Artificial NN[4].
The methods of NN will be discussed in this paper and then practical system will be devolved using matlab toolbox to show how NN be used.
محتويات مواقع أعضاء هيئة التدريس بما فيها من نصوص وملفات وصور وأبحاث وأية مواد أخرى هي مسئولية عضو هيئة التدريس بالكامل بصفته صاحب الموقع وبما له من صلاحية مطلقة في الإضافة والحذف، وتخلي الجامعة مسئوليتها عن محتويات تلك المواقع.
جميع الحقوق محفوظة © عمادة تقنية المعلومات والتعليم عن بعد 2018م ــ 1440هـ.