[DEMO] Contextuality and inductive bias in machine learning

[josephbowles]

General information

Name
Joseph Bowles

Image
see thumbnail in demonstrations/contextuality

---

Demo information

Title
Contextuality and inductive bias in quantum machine learning

Abstract
This is a demo for my recent paper https://arxiv.org/abs/2302.01365

In the demo we study the toy learning problem described in the paper, and build and train a quantum model that encodes the relevant inductive bias. The model is shown to outperform a 'generic' quantum model that does not encode this bias.

The demo is not focused much on contextuality (because it would require a lot of explanation), but rather focuses on the type of learning problem (inspired from contextuality) that is presented in the paper.

JAX is used for vectorization and JIT compilation.

Relevant links
#719 (see latest build)

[KetpuntoG]

Hey @josephbowles 😄 we do not usually open issues of this type, does this mean that it is ready for review?

[josephbowles]

haha I must have misunderstood something then. Yes it is ready for review :)

[KetpuntoG]

Awesome, thanks!
I'll close the issue then. We will now go through at least two people to take a look at the demo. I am in charge of informing the reviewers (of which I want to be one 😉)