Data compression method and device based on stacking type self-coding and PSO algorithm

Abstract

The embodiment of the invention discloses a data compression method based on stacking type self-coding and a PSO algorithm. In the method, a stacking type self-coding model is a deep learning model, the training speed of a neural network can be improved by fine tuning of a layer-by-layer learning algorithm and an overall network weight, redundant information in data is removed, the most valuable information in the original data is extracted, and meanwhile the stacking type self-coding model is endowed with a good non-linear mapping capacity by a multi-layer network structure of the stacking type self-coding model; the stacking type self-coding model can be endowed with a weight applicable to expressing a sample via the fine tuning of the layer-by-layer learning algorithm and the overall network weight, the characteristics of the data are learned, the input data does not need to have a label, a network parameter of the stacking type self-coder is set via the PSO algorithm, the accuracyand searching speed are further improved, and the technical problems that when a shallow neural network is used for compressing the data at present, the convergence speed is slow, the non-linear mapping capability is poor and the input data needs to have the label are solved.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a data compression method and device based on stacked self-encoding and PSO algorithm. Background technique [0002] The current data compression using neural network is through the shallow neural network model for data compression, and there are the following deficiencies in using the shallow neural network model for data compression: 1. Most of the current algorithms for training shallow neural network models are BP algorithm, BP algorithm The convergence speed is slow, it is easy to fall into local minimum points, and the shallow neural network model is easily disturbed by new features; 2. Due to the characteristics of the training algorithm, the number of layers of the shallow neural network model cannot be too many, and the nonlinear mapping ability is relatively weak. Poor, because the error will gradually decrease during the backpropagation process, too many layers will cause th...

AI Technical Summary

Problems solved by technology

[0003] The invention provides a data compression method and device based on stacked self-encoding and PSO algorithm, which solves the problem of slow convergence speed, poor nonlinear mapping ability and the need for input data with labels when using shallow neural networks for data compression. technical issues

Images