Model parameter optimizing method and device

Abstract

The invention is suitable for a field of information technology and provides a model parameter optimizing method and device. The method includes obtaining sample data and performing standardizing treatment on the sample data; obtaining the optimal penalty coefficient C and the optimal kernel scale Gamma of a kernel extreme learning machine through combining with a Moth optimization algorithm of chaos theory by adopting the sample data subjected to standardization; according to the sample data subjected to standardization, the optimal penalty coefficient C and the optimal kernel scale Gamma, constructing a target classification predication model. The invention solves a problem that the optimal penalty coefficient C and the optimal kernel scale Gamma cannot be obtained by utilizing a grid searching method in the prior art and is beneficial to improvement of effect of the constructed model in classification and predication of determined problems.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a method and device for optimizing model parameters. Background technique [0002] The traditional neural network method has the disadvantage of being easily trapped in a local minimum because of the gradient descent method for training and learning. At the same time, it is difficult to establish an optimal model because a large number of parameters need to be adjusted during the network construction process. In order to overcome the above shortcomings of neural networks, Professor Huang Guangbin from Nanyang Technological University and others proposed a new neural network learning method, namely extreme learning machine. However, since the input parameters of the extreme learning machine are randomly generated, the performance of the model will be unstable; in this regard, Professor Huang Guangbin and others continued to propose the kernel extreme learning mach...

AI Technical Summary

Problems solved by technology

The existing technology mainly uses the grid search method to determine the penalty coefficient C and the kernel width γ. However, the grid search method is easy to fall into the problem of local optimum, and cannot obtain the optimal penalty coefficient C and kernel width γ, which affects the model. The classification and prediction effect of

Images