Quantum Neural Information Processing

Peter J. Marcer

Vladimir G. Ivancevic, Tijana T. Ivancevic

YU Jin-shou

In the framework of quantum theory,the process of the neural unit dealing with information is explained,and quantum neural unit is proposed.The process includes two stages.The first stage is collecting macroscopical information,in which control quantum bit is produced.The second stage is dealing microcosmic information that neural unit state is changed according to control quantum bit.The whole process simulates the quantum controlled NOT gate.The synthetic datasets and real datasets are used as classification objects.Classification results of the quantum neural network are better than that of the classical neural network.Additionally,acrylonitrile reactor is used as modeling object.The proposed network shows the better performance.

Mitja Peruš, Horst Bischof

The Hopfield neural networks and the holographic neural networks are models which were successfully simulated on conventional computers. Starting with these models, an analogous fundamental quantum information processing system is developed in this article. Neuro-quantum interaction can regulate the "collapse"-readout of quantum computation results. This paper is a comprehensive introduction into associative processing and memory-storage in quantum-physical framework.

Subhash C. Kak

Huitao Shen, Pengfei Zhang, Yi‐Zhuang You +1 more

The quantum neural network is one of the promising applications for near-term noisy intermediate-scale quantum computers. A quantum neural network distills the information from the input wave function into the output qubits. In this Letter, we show that this process can also be viewed from the opposite direction: the quantum information in the output qubits is scrambled into the input. This observation motivates us to use the tripartite information-a quantity recently developed to characterize information scrambling-to diagnose the training dynamics of quantum neural networks. We empirically find strong correlation between the dynamical behavior of the tripartite information and the loss function in the training process, from which we identify that the training process has two stages for randomly initialized networks. In the early stage, the network performance improves rapidly and the tripartite information increases linearly with a universal slope, meaning that the neural network becomes less scrambled than the random unitary. In the latter stage, the network performance improves slowly while the tripartite information decreases. We present evidences that the network constructs local correlations in the early stage and learns large-scale structures in the latter stage. We believe this two-stage training dynamics is universal and is applicable to a wide range of problems. Our work builds bridges between two research subjects of quantum neural networks and information scrambling, which opens up a new perspective to understand quantum neural networks.