Integrated framework method for optimizing extremity learning machine by using genetic algorithm

Abstract

The invention discloses an integrated framework method for optimizing extremity learning machine by using a genetic algorithm. According to the method, during determining the fitness of each individual in the genetic algorithm, random drawing sample examples from a training set are used as a validation test set, so that the generalization of a trained network can be effectively improved; after the completion of the iteration, an extremity learning machine population with smaller training error is maintained in the genetic algorithm, and then based on the characteristics of the extremity learning machine, excellent individuals with smaller training errors and smaller weight output ranges are selected for integration. The method makes full use of the characteristic of fast training speed of the extremity learning machine, can optimize individuals of the extremity learning machine by using the framework of the genetic algorithm and less iteration times, and formulates a corresponding choice mechanism according to the theory of the extremity learning machine; the extremity learning machine individuals with the smaller training errors and the smaller weight output ranges are selected for network integration, so that in an acceptable training time range, generalization and network stability are remarkably improved.

Description

technical field [0001] The invention belongs to the technical fields of computing intelligence and neural network, and relates to an integrated framework method for optimizing an extreme learning machine by using a genetic algorithm. Background technique [0002] The extreme learning machine is a simple and effective method of training a single hidden layer feed-forward neural network. Unlike the traditional neural network learning algorithm that uses methods such as gradient descent to adjust the parameters in the network, the extreme learning machine randomly generates inputs. The parameters and the threshold of the hidden layer, and then the output weight is calculated by the Moore-Penrose generalized inverse matrix. The extreme learning machine obtained through the above process not only has a small training error, but also has a small output weight norm. According to Barlett's theory, in a feedforward neural network, when the training error is small, the smaller the no...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the above-mentioned extreme learning machine is easy to randomly produce poor random parameters and possible overfitting, the purpose of the present invention is to provide an integrated framework method for optimizing the extreme learning machine using the genetic algorithm, using the genetic algorithm to train and optimize the extreme learning machine and The integrated computing framework, fully utilizing the characteristics of the extreme learning machine, within an acceptable training time, the generalization ability and network stability have been significantly improved

Images