I am trying to implement arXiv:1802.06002. I do not understand how to take the data set from MNIST and apply it to a quantum circuit.

[†]: Classification with Quantum Neural Networks on Near Term Processors (Farhi & Neven, 2018)


1 Answer 1


First, they reduce the size from 28*28 to 4*4 images (by downsampling), then convert into binary values for pixels by just comparing to a value. Then, they encode the data in a quantum uniform superposition (with computational basis representing a bitstring data image with its label).

  • $\begingroup$ Can you speak more about encoding the downsampled image to be able to apply it to the quantum circuit? $\endgroup$ Commented Jul 7, 2019 at 20:59

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.