Studies the question of H-MLP (multilayer perceptron with hardlimiting activation function) network size selection for any two-class classification problem with finite samples. Based on a concept called classification complexity (CC). Meaningful theoretical results are given. An information like criterion and an algorithm are proposed for estimating the degree of CC. This estimation process presents a constructive method to construct network structure, size, and weights configuration in each layer.

This paper addresses a hybrid neural networks system, "TsingNeu-1", for large scale printed Chinese character recognition. The system, which consists of three-level structure of neural networks with feedback error control, is a well designed unbalanced hierarchical tree structure with its functional parts working in a cooperative way according to their functions. Feedback error control based on output evaluation has been adopted for improving robustness of the system. Recognition features of the Chinese characters are extracted automatically and adaptively by self-organizing learning in every stage of the recognition processes. The implemented system can recognize 3755 categories of Chinese characters and some common used punctuations with various fonts and sizes. Experimental results show that the whole system is of reasonable size, easy to train and satisfactory performance.

This paper investigates the application of TAF (trainable activation function) neural network to handwritten digit recognition. A three-layer feedforward TAF neural network is used as digits recognizer. Each TAF neuron in the hidden layer acts as a two-class classifier which distinguishes the two pattern classes from each other. The output layer gives output for decision making. While many approaches have bean suggested for this application the proposed method is new and has the advantage of small network size and good recognition performance. Experiments performed on selected digits from NIST database demonstrated that about 99% correct recognition rate has been achieved.