Incremental Neural Network Construction for Text Classification
Jenq‐Haur Wang, Hsin Yang Wang · 2014
Artificial neural network (ANN) has wide applications such as data processing and classification. However, comparing with other classification methods, ANN needs enormous memory space and training time to build the model. This makes ANN infeasible in practical applications. In this paper, we try to integrate the ideas of human learning mechanism with the existing models of ANN. We propose an incremental neural network construction framework for learning. In this framework, a neural network is incrementally constructed by the corresponding subnets with individual instances. First, a subnet maps the relation between inputs and outputs for an observed instance. Then, when combining multiple subnets the neural network keeps the ability to generate the same outputs with the same inputs. This makes the learning process unsupervised and inherent in this framework. In our experiment, Reuters-21578 was used as the dataset to show the effect of the proposed method on text classification. The experimental results showed that our method can effectively classify texts with the best F1-measure of 92.5%. It also showed the learning algorithm can enhance the accuracy effectively and efficiently. This framework also shows scalability in terms of the network size, in which the training and testing time both show a linear growth. This also validates the practical use of the method.