So there are a lot of feature mapping techniques out there for Quantum Machine Learning, but I'm not sure which one to use for my next VQC.

Can anyone explain when and why to use each of the following?

  1. Amplitude embedding
  2. Basis embedding
  3. Angle embedding

Although I understand the difference in the architecture of each method, I don't see why you would choose one over another.

Thank you!

  • 2
    $\begingroup$ there's no rules set in stone for this as far as I know. There's results connecting the expressivity of different embeddings etc (eg amplitude encoding compresses information exponentially and therefore often requires long circuits to implement, which you might not want), but what you need strongly depends on the specific context $\endgroup$
    – glS
    Commented Aug 18, 2023 at 14:32

1 Answer 1


PennyLane provides a great starting point for looking into various types and reasons for embedding: https://pennylane.ai/qml/glossary/quantum_embedding.

It is also easy to take some of the tutorials/templates and modify/run code locally on your desktop but then you can scale up/move to actual hardware by switching to a Braket backend: https://github.com/aws/amazon-braket-examples/blob/main/examples/pennylane/0_Getting_started/0_Getting_started.ipynb


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.