Norelhouda Azzizi, Abdelouhab Zaatri
Department of Mathematics
Faculty of Exact Sciences
University of Freres Mentouri
Constantine, ALGERIA
Department of Mechanical Engineering
Faculty of Engineering Sciences
University of Freres Mentouri
Constantine, ALGERIA

Abstract. For learning artificial systems as well as for living systems, it is generally proven that the learning performances improve with the experience. This paper seeks to analyze the learning process of an artificial system: a Multi-Layer Perceptron Neural Nets (MLP-NN) used for word recognition and dedicated for robot control. As the MLP requires references for the spoken words, we have provided these references by means of a supervised classifier based on minimizing the mean square error.

We are particularly interested by estimating the minimal number of trials required to ensure the recognition of some spoken words by the MLP-NN with an acceptable predefined error. To this purpose, we have experimentally performed the learning process of the recognition of some specific words. For each word, we have recorded the performance improvement with respect to the number of trials enabling to draw the learning curve. The mathematical modeling of these curves presents a bi-exponential law profile while the mathematical modeling of human performance show generally a power law profile. The obtained results have led to a better understanding of the artificial system performance under the influence of internal and external human and technological factors.

Received: February 22, 2016

AMS Subject Classification: 00A05

Key Words and Phrases: learning curve, supervised learning, MLP, mathematical modeling, neural networks, word recognition

Download paper from here.

Google Scholar; DOI (International DOI Foundation); WorldCAT.

This work is licensed under the Creative Commons Attribution International License (CC BY).