Image tensor data processing method

Abstract

The invention discloses an image tensor data processing method which can greatly reduce the number of free parameters in a model, is flexible in weight layer limitation and can be suitable for image tensor data of any order. According to the image tensor data processing method, a restricted Boltzmann machine TTRBM model with a tensor structure is introduced, input data and output data of the method are expressed by tensors, weights of an intermediate layer are also expressed by tensors, and the weights are limited to have the structure of a Trustin. The number of free parameters in an intermediate layer is controlled by adjusting the rank of tensor Train decomposition; the rank of TT decomposition is adjusted, and different feature representations of the same size are adjusted.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a method for processing image tensor data, which can be directly applied to image tensor data of any order. Background technique [0002] Restricted Boltzman Machine (RBM) is a two-layer neural network composed of visible layer and hidden layer. It is widely used in pattern recognition and machine learning because of its strong feature representation ability. The visible layer and hidden layer data in traditional RBM are expressed in vector form. [0003] However, today's real-life data often have high-dimensional properties. In order to apply RBM on these high-dimensional data, the common method is to vectorize the data. The process of vectorization often destroys the internal structure of high-dimensional data, resulting in the loss of important related information, or the problem of dimensionality disaster. In addition, RBM is a fully connected network struct...

AI Technical Summary

Problems solved by technology

Therefore, more storage space and higher computational complexity are required, which makes

Images