A feedforward neural network with function shape autotuning
Neural Networks
Face recognition using artificial neural network group-based adaptive tolerance (GAT) trees
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper a new data simulation system, based on the y and sin(x)/x functions, called YSINC Polynomial Higher Order Neural Network (YSINCPHONN) has been developed. The YSINCPHONN model provides one more opportunity to find the optimal neural network model for simulation and prediction. This paper also proves that YSINCPHONN models can converge when simulating XOR data. This study also tests rainfall data. Based on the test results, YSINCPHONN model is 0.6562% better than Polynomial Higher Order Neural Network (PHONN) model and 0.62368% batter than trigonometric Polynomial Higher Order Neural Network (THONN) model in simulating rainfall. Moreover, foreign exchange rate simulation has been tested by using YSINCPHONN models. Test results show that YSINCPHONN models are about 0.7143% to 3.3243% better than PHONN, THONN, Sigmoid Polynomial Higher Order Neural Network (SPHONN), and SINC Polynomial Higher Order Neural Network (SINCHONN) models.