EQuaTE: Efficient Quantum Train Engine for Dynamic Analysis via HCI-based Visual Feedback
Soohyun Park, Won Joon Yun, Chanyoung Park, Youn Kyu Lee, Soyi Jung,, Hao Feng, and Joongheon Kim
TL;DR
EQuaTE is a tool that uses dynamic analysis and visual feedback to help software engineers identify and modify quantum neural networks that are stuck in barren plateaus, improving quantum machine learning.
Contribution
The paper introduces EQuaTE, a novel quantum train engine that combines gradient variance plotting with HCI-based visual feedback for effective quantum neural network analysis.
Findings
EQuaTE successfully visualizes gradient variances in QNNs.
It enables detection of barren plateaus in quantum neural networks.
The tool facilitates modifications to improve QNN training efficiency.
Abstract
This paper proposes an efficient quantum train engine (EQuaTE), a novel tool for quantum machine learning software which plots gradient variances to check whether our quantum neural network (QNN) falls into local minima (called barren plateaus in QNN). This can be realized via dynamic analysis due to undetermined probabilistic qubit states. Furthermore, our EQuaTE is capable for HCI-based visual feedback because software engineers can recognize barren plateaus via visualization; and also modify QNN based on this information.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsQuantum Computing Algorithms and Architecture · Neural Networks and Reservoir Computing · Advancements in Semiconductor Devices and Circuit Design