Richard Wei

Sorry, I totally missed this issue earlier. Do you still need help on this?

It's highly unlikely that it's a problem with the usage of Substring. What's your string input when you are parsing two terms? And what is it when you are parsing...

Good job finishing the project @param087 and @vantony1! The work you've done is impressive and let's talk about next steps soon. One great way is to have you present at...

I don't have the best guidelines here, but we should check for convergence for very trivial models (which we probably don't have anymore) and test layer gradients against a Python...

Sure thing!

`#tfop` are not differentiable and will lead to undefined behavior (so don't use them!). You can define your differentiable version of `Tensor.concatenated(...)` locally in your file using the `differentiableFunction(from:)` operator...

Excellent!

Could you help file a bug on https://bugs.swift.org with the reproducer?

Note: There are two places where reabstracting back to `@callee_guaranteed` is needed. - `Builtin.applyDerivative*` call sites. This is because the caller expects the result to have the formal lowered type....

Thanks for the ping. I'm giving this a shot this weekend.