Feasible Architecture for Quantum Fully Convolutional Networks

Abstract

Fully convolutional networks are robust in performing semantic segmentation, with many applications from signal processing to computer vision. From the fundamental principles of variational quantum algorithms, we propose a feasible pure quantum architecture that can be operated on noisy intermediate-scale quantum devices. In this work, a parameterized quantum circuit consisting of three layers, convolutional, pooling, and upsampling, is characterized by generative one-qubit and two-qubit gates and driven by a classical optimizer. This architecture supplies a solution for realizing the dynamical programming on a one-way quantum computer and maximally taking advantage of quantum computing throughout the calculation. Moreover, our algorithm works on many physical platforms, and particularly the upsampling layer can use either conventional qubits or multiple-level systems. Through numerical simulations, our study represents the successful training of a pure quantum fully convolutional network and discusses advantages by comparing it with the hybrid solution.

References in corpus (13)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Advances in Quantum Metrology
• The theory of variational hybrid quantum-classical algorithms
• LSTM Fully Convolutional Networks for Time Series Classification
• Quantum Convolutional Neural Networks
• A class of quantum many-body states that can be efficiently simulated
• Demonstration of a small programmable quantum computer with atomic qubits
• Quantum computing for finance: overview and prospects
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Crossover Between Non-Markovian and Markovian Dynamics Induced by a Hierarchical Environment
• Quantum Criticality and the Kondo Lattice
• Exact non-Markovian master equations for multiple qubit systems: quantum trajectory approach