Neural net data generation method for nonlinear device modeling

Abstract

The invention belongs to the field of a nonlinear device design technology, and relates to a neural net data generation method for nonlinear device modeling, comprising, 1), acquiring main input and output sample data of a nonlinear device; 2), determining numeric area of each input parameter and constructing an initial training data acquisition set and an initial testing data acquisition set; 3), figuring out all subspace effective errors and finding out the greatest effective error and comparing the greatest effective error with the standard error value, if the result is smaller, it is shown that sufficient training data are obtained, or, otherwise, picking out the subspace with the most effective error and comparing each parameter dimensionality error value of the subspace error and determining the input parameter with the most dimensionality error; in the subspace with the most effective error, picking out all midpoints on the input parameter dimensionality with the most dimensionality error, acquiring new training data, performing space splitting and turning to 3). The neural net data generation method can save vast time and energy for next neural net training.

Description

Technical field [0001] The technical field of nonlinear device design of the present invention relates to a method for generating neural network training data for nonlinear device modeling. Background technique [0002] In nonlinear device modeling, traditional computer-aided design technology (CAD) has been widely used, and a considerable number of various device models have been produced. However, with the continuous emergence of new technologies, new materials and non-traditional devices, traditional CAD technology has been difficult to meet our actual requirements. In order to fully describe the characteristics of the new nonlinear device itself and grasp the changes in the physical and geometric properties of the device, neural network technology, as a new modeling technology, has been increasingly used in the field of nonlinear device modeling in recent years. [0003] Neural network technology is an algorithmic mathematical model that imitates the behavior characteri...

AI Technical Summary

Problems solved by technology

However, even though this algorithm has been greatly improved over traditional algorithms, the time-consuming of this algorithm is still very long, which has become a major obstacle in the field of neural network nonlinear device modeling

The main defects of this algorithm are as follows: Since the algorithm divides the sampling space regularly, the data obtained in each dimension is used as training data, so that a lot of redundant training data is collected, which leads to a large amount of calculation of the entire algorithm and consumes a lot of time. quite a long time

Images