Quantum Train: A Novel Hybrid Quantum-Classical Machine Learning Approach in the Model Compression Perspective

Share this post:

日期	2024-09-16

時間	12:10-13:00

地點	理學教學新大樓物理系1F 36173會議室

領域	Quantum Information Science

講者	管希聖教授 - 台灣大學物理系

題目	Quantum Train: A Novel Hybrid Quantum-Classical Machine Learning Approach in the Model Compression Perspective

摘要	We introduce the quantum-train (QT) framework, a novel approach that integrates quantum computing with classical machine learning algorithms to address significant challenges in data encoding, model compression, and inference hardware requirements. Even with a slight decrease in accuracy, QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model, which significantly reduces the parameter count from M to O(polylog(M)) during training. Our experiments demonstrate QT’s effectiveness in classification tasks, offering insights into its potential to revolutionize machine learning by leveraging quantum computational advantages. This approach not only improves model efficiency but also reduces generalization errors, showcasing QT’s potential across various machine learning applications.

2024-09-16 12:10:00 ~ 2024-09-16 13:00:00