Tom Breloff

> If by "deep" you mean multi-layer, then if definitely does that. Cool! Do you have any issues with backpropagating errors through the gating mechanics of the LSTM? Do you...

> It seems a little like a blob package atm. Yes certainly true. When I started it, I didn't really intend for it to be a package others used... mostly...

> You probably don't need version control at the download site, only at the repository level I don't understand what you mean by this. When you say "download site", do...

Well 3 is already implemented. Try xerror and yerror attributes. Yes 2 and 4 should be recipes of some sort. On Friday, September 30, 2016, Michael Krabbe Borregaard < [email protected]>...

Hey @c42f I would love to have something for super-fast point clouds without too many bells and whistles (as a Plots backend I mean). If we commit to only supporting...

Is `calibrate!` the same as `fit!`? If not, how do they differ? It would be best to unify the verbs as much as possible.

I see... and I guess the verb makes sense, it just also sounds similar to `fit`. Here's some other possible verbs, but maybe `calibrate` is the best: - align -...

> What about a Normal(mu,sigma) taken at (mu,sigma)=(2.3,.7)? There is no data but you can simulate from it, it can return coef() etc. (This is what I was calling a...

> I'd call Normal(μ, σ) with (μ,σ)=(2.3,.7) a distribution and not model. I get what you mean, but in some sense: `Distribution If μ and σ were left unspecified, I'd...

@BenConnault From your posts, I get the feeling that, from your perspective, `calibrate` is the same thing as `construct`. i.e. There's no need for a verb... just a type constructor.