This repository has been archived by the owner on Mar 23, 2021. It is now read-only.
[ENTRY][Floq] Trainable Quantum Embedding Kernels with PennyLane #67
Labels
floq
This project used the Floq simulator service
submission
This is an official entry for the QHack Open Hackathon
Team Name:
Notorious FUB
Project Description:
A central bottleneck of kernel-based machine learning is the choice of the kernel itself. This problem, called model selection, saw some novel approaches in the 2000s, where a couple quantities were proposed as kernel quality estimators. It was proved that a kernel with a high polarization or alignment would have good classification and generalisation behavior. One would use this instead of an exhaustive parameter search e.g. when choosing the value of the variance for the everpresent gaussian kernels.
Recent research efforts have been made in studying the use and performance of quantum kernels in learning models. We propose to leverage the theoretical results from those early papers into studying the viability of trainable quantum kernels. We attempt this under the lens of the full-stack, providing a general purpose new module to Pennylane for further implementation of kernel methods. This includes methods e.g. for dealing with noise in the kernel matrix estimation, and for maximizing the kernel alignment, out of the shelf. In add, we provide demos and analysis on real quantum hardware as well as high-performing classical simulators.
Presentation:
https://github.com/thubregtsen/qhack/blob/master/submission/blogpost.md
https://github.com/thubregtsen/qhack/blob/master/submission/kernel_demonstration.ipynb
https://github.com/thubregtsen/qhack/blob/master/submission/floq_MNIST_demonstration.ipynb
Source code:
PennyLaneAI/pennylane#1102
https://github.com/thubregtsen/qhack/tree/master/submission
The text was updated successfully, but these errors were encountered: