Parallel Hybrid Networks: an interplay between quantum and classical neural networks

Abstract

Quantum neural networks represent a new machine learning paradigm that has recently attracted much attention due to its potential promise. Under certain conditions, these models approximate the distribution of their dataset with a truncated Fourier series. The trigonometric nature of this fit could result in angle-embedded quantum neural networks struggling to fit the non-harmonic features in a given dataset. Moreover, the interpretability of neural networks remains a challenge. In this work, we introduce a new, interpretable class of hybrid quantum neural networks that pass the inputs of the dataset in parallel to 1) a classical multi-layered perceptron and 2) a variational quantum circuit, and then the outputs of the two are linearly combined. We observe that the quantum neural network creates a smooth sinusoidal foundation base on the training set, and then the classical perceptrons fill the non-harmonic gaps in the landscape. We demonstrate this claim on two synthetic datasets sampled from periodic distributions with added protrusions as noise. The training results indicate that the parallel hybrid network architecture could improve the solution optimality on periodic datasets with additional noise.

arXiv comment12 pages, 10 figures

References in corpus (16)

• A variational eigenvalue solver on a quantum processor
• Barren plateaus in quantum neural network training landscapes
• Parameterized quantum circuits as machine learning models
• Fourier Neural Operator for Parametric Partial Differential Equations
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• A rigorous and robust quantum speed-up in supervised machine learning
• Generalization in quantum machine learning from few training data
• Hybrid quantum neural network for drug response prediction
• Quantum Machine Learning: from physics to software engineering
• Quantum algorithms applied to satellite mission planning for Earth observation
• Generalization despite overfitting in quantum machine learning models
• Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Practical application-specific advantage through hybrid quantum computing

Cited by in corpus (10)

• Quantum machine learning for image classification
• Hybrid quantum neural network for drug response prediction
• Quantum algorithms applied to satellite mission planning for Earth observation
• Hybrid quantum image classification and federated learning for hepatic steatosis diagnosis
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
• Hybrid quantum cycle generative adversarial network for small molecule generation
• An exponentially-growing family of universal quantum circuits
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Photovoltaic power forecasting using quantum machine learning
• Method for noise-induced regularization in quantum neural networks