New quantum encoding method boosts neural network performance

Researchers have introduced a novel data-loading technique for quantum neural networks called shot-based quantum encoding (SBQE). This method addresses the limitations of existing encoding schemes by utilizing the hardware's native resource, shots, to distribute data across multiple quantum states. SBQE effectively creates a mixed-state representation that is linearly composed with nonlinear activation functions, mimicking a multilayer perceptron. Benchmarks on image datasets like Semeion, Fashion MNIST, and MNIST demonstrate that SBQE achieves competitive or superior test accuracies compared to amplitude encoding and classical networks, without requiring data-encoding gates. AI

IMPACT This new encoding method could improve the efficiency and performance of quantum machine learning models.

RANK_REASON The cluster contains a research paper detailing a new method for quantum neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Alexey Melnikov
• Fashion MNIST
• MNIST database
• multilayer perceptron
• noisy intermediate-scale quantum hardware
• quantum neural networks
• Shot-based quantum encoding

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →