Hierarchical Semantic Perceptron Grid Based on Neural Network

A hierarchical semantic perceptron grid architecture based neural network has been proposed in this paper, the semantic spotting is a key issue of this architecture, for finding solution to this problem, firstly we has formulated it, then a semantic neural network classifier frame has been proposed. And experiment results of this scenario were presented, to evaluate the effectiveness of this scenario, we compare this scenario with the SVM, NNet, KNN and NB, the average experimental results of the scenario are obviously superior to other conventional approaches.