Saki’s Spaces

👉icon：https://www.twitch.tv/vedal987/schedule 大香蕉一条大香蕉你的感觉真的很奇妙~🎵

建议使用aquai.notion.site访问本站。

My primary research focus is on the intersection of quantum computing and artificial intelligence, exploring both how quantum technology can enhance AI (Quantum for AI) and how AI can advance quantum computing (AI for Quantum).

In the Quantum for AI, I am particularly interested in leveraging the capabilities of quantum computing in high-dimensional spaces to enhance classical deep learning techniques. This includes utilizing quantum parallelism to accelerate computations in large-scale models like Transformers and GNNs. I am also focused on developing quantum-enhanced representation learning (deep learning) methods to extract complex features more efficiently from data, capitalizing on the ability of quantum systems to navigate exponentially large state spaces. I am particularly intrigued by applying quantum information theory to optimize the Information Bottleneck principle, seeking to balance compression and information preservation in AI models more effectively.

On the AI for quantum side, I am interested in applying classical AI techniques to address challenges in quantum computing. This involves using deep learning to optimize quantum circuit designs, potentially by adapting attention mechanisms from transformers to model quantum systems or employing representation learning to identify optimal quantum gate sequences.

The goal is to make quantum computing practical, whether it is based on quantum-inspired algorithms or using real quantum hardware to run quantum algorithms.

Research interests:

Quantum Information, Quantum Machine Learning, Quantum Algorithms, Artificial Intelligence, Cybersecurity

Publication:

Hybrid Quantum-Classical Convolutional Neural Networks for Image...

The growing complexity and scale of image processing tasks challenge classical convolutional neural networks (CNNs) with high computational costs. Hybrid quantum-classical convolutional neural...