Improved top speed learning model and method for classifying modes of improved top speed learning model

Abstract

The invention provides an improved top speed learning model and a method for classifying modes of the top speed learning model, discloses an efficient neural network rapid learning method and a limited top speed learning machine and belongs to the field of mode identification and machine learning. The improved top speed learning model comprises (1) a concept of a limited parameter space, (2) a hypersphere limited condition in the limited parameter concept and (3) output weight learning. According to the concept of the limited parameter space, a lateral inhibition mechanism based on sample prior information is adopted and the content is particularly shown on the aspect of generation of a connection weight from an input layer to a hidden layer; according to the hypersphere limited condition in the limited parameter concept, selection of the connection weight from the input layer to the hidden layer is limited to a hypersphere; according to output weight learning, after a weight of the hidden layer is selected from the limited parameter space, learning is trained through a top speed learning machine model based on least squares, and finally an output weight of the model is obtained. According to the method, the classification and identification effects of the model can be greatly improved, and the training speed can be greatly increased.

Description

technical field [0001] The invention relates to pattern classification of images, voices and various signals, in particular to an improved extremely fast learning model and a pattern classification method thereof. Background technique [0002] In terms of pattern classification based on fast and extremely fast learning, the Extreme Learning Machine (ELM) can quickly perform pattern classification. The algorithm has the advantages of fast learning speed, no need for too much manual intervention on the parameters in the learning process, and strong generalization ability. Moreover, the algorithm has better generalization performance than traditional pattern classification algorithms, such as support vector machine (Support Vector Machine, SVM), BP neural network, RBF neural network, etc. Due to the very good classification and prediction performance of the extremely fast learning machine, as well as the learning and training speed, the extremely fast learning machine has been...

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problem of weak generalization ability of the above-mentioned extremely fast learning and pattern classification models, the purpose of the present invention is to propose an improved extremely fast learning model and a pattern classification method based on the improved model, so as to realize the processing of arbitrary images, voices and various signals. The purpose of efficient pattern classification

Images