Method for improving pattern recognition precision trough combining with data representation and pseudo-inverse learning auto-encoder

Abstract

The invention relates to a method for improving the pattern recognition precision trough combining with data representation and a pseudo-inverse learning auto-encoder. Based on the pattern recognitiontheory where a sample is linearly inseparable in a low-dimensional space and may be separable in a high-dimensional space, the method employs the advantages of quick learning based on the pseudo-inverse learning auto-encoder, and can achieve the quick and accurate training of a stacked auto-encoder deep neural network. The method comprises the steps: increasing the dimensions of data through receptive fields: employing four specific receptive field functions for increasing the dimensions of original data, wherein the four receptive fields are a receptive field based on a kernel function, a receptive field based on function connection, a receptive field based on nonlinear transformation, and a receptive field based on random mapping; employing the data transformed through the receptive fields as the input of the auto-encoder, and employing a pseudo-inverse learning method for quickly obtaining a weight matrix of a neural network. The method has remarkable advantages in improving the precision of pattern recognition, is suitable for most of regression and classification problems, does not need complex counterpropagation calculation and time-consuming super-parameter optimization, and facilitates the hardware implementation at a mobile terminal.

Description

technical field [0001] The invention relates to the technical fields of pattern recognition, neural network and machine learning, in particular to a method for improving pattern recognition accuracy by combining data representation and pseudo-inverse learning autoencoder. Background technique [0002] An artificial neural network is a neural network that is artificially constructed on the basis of human understanding of its brain neural network and can achieve certain functions. In fact, it is a complex network composed of a large number of simple neurons connected to each other, which is highly nonlinear, parallel, and capable of complex logic operations and nonlinear relationship realization systems. [0003] Autoencoder is a commonly used basic unit of deep neural network. This unit is essentially a single hidden layer feed-forward neural network model. feature learning. The self-encoder is composed of an encoder (encoder) and a decoder (decdoer). The encoder encodes th...

AI Technical Summary

Problems solved by technology

These algorithms need multiple iterations on the training data set to get the optimal solution. When the amount of data is large, the training process is very time-consuming.

Images