David Mertz

0

votes
0

answer
4

views

Need very different learning rate for manual updates vs. using model

I am currently just trying to write some pedagogical material, in which I borrow from some common examples that have been reworked numerous times on the web. I have a simple bit of code where I manually create tensors for layers, and update them within a loop. E.g.: w1 = torch.randn(D_in, H, dtype=...
David Mertz
0

votes
0

answer
20

views

“Complete” a set algorithmically efficiently

I have this little toy problem that is bothering me. I think it is equivalent to any number of equivalent problems of more seriousness. No, this is not a homework or interview question... although possibly I will use it to interview people at some point if I feel like I know a provably optimal solu...
David Mertz
2

votes
3

answer
33

views

Deferring a computation in custom object until data available

I have a custom class like the below. The idea, as the naming suggests, is that I want to evaluate a token stream in a parser-type tool. Once a bunch of constructs have been parsed out and put into data structures, certain sequences of tokens will evaluate to an int, but when the data structures a...
David Mertz