This chapter discusses development, application, and enhancement of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The dual objectives of developing the algorithms are (1) to generate good predictive models comparable in performance to the original artificial neural network (ANN) models and (2) to “open up” the black box of a neural network model and provide explicit information in the form of rules that are expressed as linear equations. The enhanced PWL-ANN algorithm improves upon the PWL-ANN algorithm because it can locate more than two breakpoints and better approximate the hidden sigmoid activation functions of the ANN. Comparison of the results produced by the two versions of the PWL-ANN algorithm showed that the enhanced PWL-ANN models provide higher predictive accuracies and improved fidelities compared to the originally trained ANN models than the PWL-ANN models.
This chapter discusses development, application, and enhancement of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The dual objectives of developing the algorithms are (1) to generate good predictive models comparable in performance to the original artificial neural network (ANN) models and (2) to “open up” the black box of a neural network model and provide explicit information in the form of rules that are expressed as linear equations. The enhanced PWL-ANN algorithm improves upon the PWL-ANN algorithm because it can locate more than two breakpoints and better approximate the hidden sigmoid activation functions of the ANN. Comparison of the results produced by the two versions of the PWL-ANN algorithm showed that the enhanced PWL-ANN models provide higher predictive accuracies and improved fidelities compared to the originally trained ANN models than the PWL-ANN models.
Engineers often meet function regression problems in manufacturing. In this work, we use artifical neural network to solve this problem. We choose a typical function as the target function. Since the input value of the function is continuous, the output of the regression model should also have a continuous value range. We implement the feed forward neural network with back propagation learning algorithm, investigate different network parameters, and compare several different training algorithms. The performance assessment based on the test dataset is also discussed.
Projection neural network for a class of sparse regression problems with cardinality penalty
