A HYBRID APPROACH FOR ARABIC LITERAL AMOUNTS RECOGNITION

ABSTRACT The challenge of hybrid learning systems is to use the information provided by one source of information to compensate information missing from the other source. The neuro–symbolic combination represents a promising research way. The synergy between the symbolic (theoretical) and neural (empirical) approaches makes their combination more effective than each of them used alone. In this article, we describe an Arabic literal amount recognition system that uses a neuro-symbolic classifier. For this purpose, we first extract structural features from the words contained in the amounts vocabulary. Then, we build a symbolic knowledge base that reflects a classification of words according to their features. In a third step, we use a translation algorithm (from rules to neural network) to determine the neural network architecture and to initialize its connections with specific values rather than random values, as is the case in classical neural networks. This construction approach provides the network with theoretical knowledge and reduces the training stage, which remains necessary because of styles and writing conditions variability. After this empirical training stage using real examples, the network acquires a final topology, which allows it to recognize new handwritten amounts.