Due to its parallelism property in processing the data, the Artificial Neural Networks (ANN) has been gaining wide interest in recent years as a tool for processing data. Different ANN architectures have been defined for various...
moreDue to its parallelism property in processing the data, the Artificial Neural Networks (ANN) has been gaining wide interest in recent years as a tool for processing data. Different ANN architectures have been defined for various applications. Yet, a number of difficulties existed when building an ANN like training time, over-training problem, retraining of the net for new types of data. This paper presents a new ANN architecture, which we called "MS/Ayad-Marwan Network" (MS stands for Multi-Stage), that compose of supernet and subnets ("Stage" architecture). The "Computer-Assisted" approach is used to develop this NN. Also, in this paper, a new learning algorithm has been proposed, which is required for adjusting weighting values for MS/Ayad-Marwan neural network. We called this algorithm a "hybrid unsupervised/supervised learning paradigm" This learning algorithm is used for training both supernet and subnets. Inheritance property of OOP plays an important role in the reasoning approach of MS/Ayad-Marwan Network, in that it deduces the final solution by gathering the property of the super network with the properties of its sub(s), to reach the ultimate goal. Thus, the results become more accurate. We called his reasoning approach " Deductive auto-associative recalling". MS/Ayad-Marwan ANN has been applied to an Automatic Speech Recognition (ASR) application. This new network architecture is being able to recognize phonemes with >91% accuracy. We note through the results a promising advancement has been reached and hence a Multi-Stage strategy is useful in applications of "high changeable data" property, like ASR. "MS/Ayad-Marwan" Neural Network has been implemented and tested using MATLAB, as a part of the ASR system.