QUANTUM ERROR CORRECTION DECODING METHOD AND APPARATUS BASED ON NEURAL NETWORK, AND CHIP

摘要

Disclosed are a quantum error correction decoding method and apparatus based on a neural network, and a chip, which relate to the technical field of artificial intelligence and quanta. The method comprises: acquiring error symptom information of a quantum circuit; performing block feature extraction on the error symptom information by means of a neural network decoder, so as to obtain feature information (502); and performing fusion decoding processing on the feature information by means of the neural network decoder, so as to obtain error result information, wherein the error result information is used for determining a data quantum bit, which has an error, in the quantum circuit and a corresponding error type (503). According to the method, a block feature extraction means is used, such that the number of channels of feature information obtained by means of each instance of feature extraction is reduced, and input data obtained by means of the next instance of feature extraction is reduced, thereby facilitating a reduction in the number of feature extraction layers in a neural network decoder, such that the depth of the neural network decoder is reduced, the decoding time thereof is correspondingly shortened, and the requirement for real-time error correction is thus satisfied.