README.md

quantum-neural-network

Exploring Hybrid quantum-classical Neural Networks with PyTorch and Qiskit

🎉Qiskit Hackathon Korea 2021 : Community Choice Award Winner🎉

Team "Quanputing"

name	github	role
Kifumi Numata	@kifumi	Coach, Qiskit Advocate
Anna Phan	@attp	Coach, Qiskit Advocate
Dohun Kim	@yh08037	Code development - model1/model2
Yunseo Kim	@Yunseo47	Code development - model2, Presentation
Jaehoon Hahm	@Jaehoon-zx	Create presentation slides, Presentation
DaeHeon Yoon	@Greathoney	Code development - model1, Create presentation slides
Yoon Kwon	@vhapfks	Create presentation slides
Eunchan Lee	@purang2	Code development - model1

Model 1. CNN with Quantum Fully Connected Layer

Build MNIST multi-label classifiers using classical convolution layers and quantum fully-connected layers.

Model 2. CNN with Quantum Convolution Layer

Build MNIST multi-label classifiers using quantum convolution layers and classical fully-connected layers.

References

Model 1. CNN with Quantum Fully Connected Layer

• Hybrid quantum-classical Neural Networks with PyTorch and Qiskit (Qiskit textbook)
• Gradients of parameterized quantum gates using the parameter-shift rule and gatedecomposition (arxiv)

Model 2. CNN with Quantum Convolution Layer

• Quanvolutional Neural Networks (Pennylane demo)
• arxiv-Quanvolutional Neural Networks: PoweringImage Recognition with Quantum Circuits (arxiv)