Quantum effects in neural networks

Thomas Filk A

Jincheng Zhang

Quantum-Guided Neural Network Propagation (QGNNP) is a novel technique for accelerating neural network training by leveraging quantum mechanics to enhance gradient calculations. Traditional methods often struggle with the computational complexity of training large neural networks, particularly during optimization. This paper introduces a QGNNP architecture that utilizes quantum gates to significantly speed up gradient computations, leading to improved learning speed and generalization capabilities. We demonstrate the effectiveness of QGNNP through theoretical analysis and empirical testing on a diverse set of neural network architectures. This research addresses a critical bottleneck in neural network development, offering a promising path towards more efficient and robust machine learning models.

Dongxiang Nan, Yunsheng Zhang

Quantum Neural Networks (QNN) is a burgeoning new field built upon the combination of classical neural networks and quantum computations, which has many problems needed to solve. The predictive model of QNN is an issue that must be settled to develop QNN based on proportional integral derivative neural networks and quantum computation, which can be so called generalized quantum neural networks (GQNN). Firstly, we describe the theory of quantum computation and neural networks. Secondly, it can realize the algorithm of prediction to construct the modeling of generalized quantum neural networks for those complexity nonlinear systems. Finally, using an example explains the model of generalized quantum neural networks. The computational results shows that GQNN is more effective than conventional neural networks.

Moolchand Sharma, Nebojša Bačanin, Tarik Ahmed Rashid

Xi Liu, Yujun Zhao, Chun Yu Wan +2 more

We introduce effective field neural networks (EFNNs), a new architecture based on continued functions-mathematical tools used in renormalization to handle divergent perturbative series. Our key insight is that neural networks can implement these continued functions directly, providing a principled approach to many-body interactions. Testing on three systems (a classical three-spin infinite- range model, a continuous classical Heisenberg spin system, and a quantum double exchange model), we find that EFNN outperforms standard deep networks, ResNet, and DenseNet. Most striking is EFNN's generalization: Trained on 10×10 lattices, it accurately predicts behavior on systems up to 40×40 with no additional training-and the accuracy improves with system size, with a computational time speedup of 10^{3} compared to ED for 40×40 lattice. This demonstrates that EFNN captures the underlying physics rather than merely fitting data, making it valuable beyond many-body problems to any field where renormalization ideas apply.

Elizabeth Behrman, L.R. Nash, James E. Steck +2 more