Method for compressing computed hologram by adopting quantum neural network with optimized initial weight

Abstract

The invention discloses a method for compressing a computed hologram by adopting a quantum neural network with optimized initial weight, and belongs to the technical field of the compressed transmission of the computed hologram. On the basis of transmitting the computed hologram in the compressed way by the quantum BP neural network, the method comprises the following steps: pre-training by utilizing a computed hologram training set to acquire quantum BP neural network optimized initial weight; accelerating the convergence process of the pre-training network by setting the pre-trained parameter random initialization variance, and performing secondary network fine-tuning training on the optimized initial weight acquired through pre-training for the given holographic compressed data, and dynamically adjusting the network learning rate in the optimization process so as to accelerate the compressed transmission process of the quantum BP neural network. The training on the compressed transmission network structure can be accomplished by using less iteration times without changing the basic structure of the original quantum BP neural network, the compression speed on the computed hologram by the quantum BP network is accelerated, and the quality of the reproductive image of the hologram can be guaranteed.

Description

technical field [0001] The invention provides a method for compressing and computing a hologram using a quantum neural network with optimized initial weights, and specifically relates to the technical field of compression and transmission of a computing hologram. technical background [0002] The computational hologram method has the characteristics of flexibility, simplicity, and convenience. It avoids the complicated optical system and tedious preparation process of traditional optical holography, and can obtain effects that are difficult to achieve with artificially designed optical holography. The value of each point on the calculated hologram is the result of the interference between the diffracted wave and the reference light, covering all the information of the object, and each hologram contains a large amount of redundant information, which creates higher requirements for the storage and transmission of information , also limits the development of computational holog...

AI Technical Summary

Problems solved by technology

But the problem is that the quantum BP neural network is randomly initialized, which will make the initial weight of the network far from the optimal weight, and the network still needs more iterations to converge.

Images