A deep learning method for ultra-high-dimensional data reconstruction based on wavelet analysis

Abstract

The invention discloses a deep learning method for ultra-high-dimensional data reconstruction based on wavelet analysis, which uses high-dimensional and high-order discrete wavelet packet transformation to expand high-dimensional data to different frequency domain channels, and combines multiple parallel neural networks to realize The reconstruction task of high-dimensional data is carried out; data preprocessing is performed first, and then the wavelet packet coefficients of different frequency band subdomains are transformed into wavelet packet coefficients, which are input to build and train an independent network for it, and the output of the network is reconstructed through inverse wavelet packet transformation. The original image. The invention utilizes the independent property of each frequency domain after the wavelet transform of high-dimensional data, and utilizes GPU memory in parallel, which accelerates the training process of the neural network, and makes possible the artificial task of deep learning originally limited by hardware computing resources. The invention also generalizes to segmentation and generation tasks. For the segmentation task, the U‑net network output is deconvolutionally upsampled to the original image resolution segmentation labels. For the generation task, the neural network of each channel is changed to GAN.

Description

technical field [0001] The invention relates to the technical fields of image processing and neural network, in particular to a deep learning method for ultra-high-dimensional data reconstruction based on wavelet analysis. Background technique [0002] The traditional wavelet transform is proposed to solve the loss of time domain information in Fourier transform. In the field of image processing, fast discrete wavelet transform applies a series of filters to expand image information into different independent frequency domain subbands. And expressed by wavelet coefficients. [0003] CNN is the basis of the neural network that processes the image field. The convolutional layer is the core of CNN. It extracts the detailed information of the image through a series of filters and generates a feature vector map. The pooling layer introduces invariance to CNN, and at the same time downsamples to expand the receptive field of the convolution kernel of the next layer, and the netwo...

AI Technical Summary

Problems solved by technology

[0006] In the prior art, DTI (Diffusion Tensor Imaging, Diffusion Tensor Imaging) is a method to describe the brain structure through multi-directional MRI scan data. Usually, the scan data of an individual subject is several gigabytes (GB), and the depth Learning often requires a huge sample size, and the data directly involved in training is about 100GB-200GB, but the memory capacity of the current deep learning chip is limited, such as NVIDIA Tesla V100 only supports 32GB The data is stored in the video memory of the deep learning chip for deep learning training

Images