A learning algorithm of convolution neural network based on limit learning machine

Abstract

The invention discloses a convolution neural network learning algorithm based on a limit learning machine, the algorithm is based on the idea of self-encoding to learn the convolutional filter with bias. Firstly, the data matrix is used to generate the standardized training data with the mean value of 0 and variance of 1. Secondly, the data matrix is used to generate the standardized training datawith the mean value of 0 and variance of 1. Then the convolution deviation is processed, the intercept term is added, and the normalized input and intercept terms are reconstructed so that the objective matrix becomes a formula shown in the specification. Given input and objective matrix, and reshaping matrix are used to obtain a filter. The invention is based on an automatic coding limit learning machine, which learns a convolution filter, and is used for training arbitrary convolution neural network to work, dealing with the deviation of the filter, and reconstructing a standardized input with an intercept term. The invention is a hierarchical training process, does not need the entire classification model to extract arbitrary features, improves the training speed, realizes a competitive result in the generalization performance, and exceeds the BP in the training speed. CNN; while memory consumption is reduced.

Description

technical field [0001] The present invention relates to the technical field of computer artificial intelligence, specifically a convolutional neural network learning algorithm based on an extreme learning machine. This algorithm is based on the idea of ​​self-encoding to learn a convolution filter with deviations. Through reconstruction, it has Normalized input for the intercept term to close the gap between extreme learning machines and deep learning. Background technique [0002] Thanks to deep learning breakthroughs in the ImageNet Large-Scale Visual Recognition Challenge, all winning architectures have a convolutional structure. Moreover, many convolutional neural networks (referred to as CNN) have been successfully applied in different fields, such as object recognition, speech recognition, natural language processing and other fields. The convolutional neural network is trained with the BP algorithm by backpropagating the classification error, and the gradient descent...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a kind of convolutional neural network learning algorithm (abbreviation ELM-CNN) based on extreme learning machine, learn the convolution filter based on extreme learning machine with faster frame, be used for training arbitrary convolutional neural network Network architecture, a qualitative and quantitative comparison with a system based on BP training model to solve the problems of slow test time and large memory consumption in the existing technology

Images