Incremental learning for recognizing handwritten characters using neural networks
Yoh‐Han Pao, Myungsook Klassen · 1989
Artificial Neural Networks (ANNs) are parallel distributed processing machines. The unique characteristics of ANNs are: fault tolerance, robustness, plasticity and generalization. These offer great potential in many AI applications such as character recognition. Handwritten character recognition is an intrinsically interesting problem, but the difficulties of this task are the many variations in the characters. A robust new incremental learning method, which combines supervised and unsupervised learning paradigms implemented by the Functional Link Net, is illustrated with experimental results. Clustering, based on unsupervised learning, classifies the input data into several categories. The supervised learning paradigm then further classifies the data in the clustered categories.