1

I am trying to design a model using Q#'s machine learning library that takes in two features (real numbers from 0 to 1) and classifies as 0 or 1.

So how do I decide which Rotations and what seeds to use?

```
ControlledRotation((0, new Int[0]), PauliY, 0)
```

I tried using this as the rotation gate but it gave an inaccurate model for many different seed values.

I also tried combining gates:

```
ControlledRotation((0, new Int[0]), PauliY, 0),
ControlledRotation((0, new Int[0]), PauliX, 1)
```

but this also gave an inaccurate model.

There must surely be a way to analyse what kind of gates to use and not just trial and error. What kind of analysis would be appropriate?

Selecting the model structure based on the data you need to classify is part of the challenge. In the warmup round the problems were possible to solve using just one qubit, but as you see in the main round that's not sufficient. You will want to use feature engineering to have more than 2 features and use multi-qubit models. And that's all we should say until the end of the contest :-) – Mariia Mykhailova – 2020-06-19T23:13:48.490

@MariiaMykhailova Okay I see. Thanks a lot for your help. – Shreyas Pradhan – 2020-06-20T10:04:54.313