Q-RUN: Quantum-Inspired Data Re-uploading Networks
This work provides a scalable, drop-in replacement for neural network layers that improves performance across various architectures, addressing a practical bottleneck in machine learning.
The paper tackles the scalability limitations of quantum neural networks by introducing a quantum-inspired classical model called Q-RUN, which reduces model parameters and decreases error by approximately one to three orders of magnitude on certain tasks compared to state-of-the-art layers.
Data re-uploading quantum circuits (DRQC) are a key approach to implementing quantum neural networks and have been shown to outperform classical neural networks in fitting high-frequency functions. However, their practical application is limited by the scalability of current quantum hardware. In this paper, we introduce the mathematical paradigm of DRQC into classical models by proposing a quantum-inspired data re-uploading network (Q-RUN), which retains the Fourier-expressive advantages of quantum models without any quantum hardware. Experimental results demonstrate that Q-RUN delivers superior performance across both data modeling and predictive modeling tasks. Compared to the fully connected layers and the state-of-the-art neural network layers, Q-RUN reduces model parameters while decreasing error by approximately one to three orders of magnitude on certain tasks. Notably, Q-RUN can serve as a drop-in replacement for standard fully connected layers, improving the performance of a wide range of neural architectures. This work illustrates how principles from quantum machine learning can guide the design of more expressive artificial intelligence.