.png){kind=icon}
.png){kind=icon}
Return
Analysis and synthesis of feature map for kernel-based quantum classifier
.png){kind=icon}
PRE
AI
DOI：10.1007/s42484-020-00020-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional datasets. Also, a synthesis method, which combines different kernels to construct a better-performing feature map in a lager feature space, is presented.
Keywords:
Quantum computing
Support vector machine
Kernel method
Feature map
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.