Viewing profile — wxs

If you like this you may enjoy the "Pink Trombone" an interactive speech synthesizer that you control by moving around the virtual tongue and lips: https://dood.al/pinktrombone/

> of consciousness, we have agents that perceive the environment and act, in order to maximize rewards I don't believe "agents acting to maximize rewards" is a good description of …

Like Bret Victor? Who seems to have been involved in presenting this to Jobs? I'd say he's a pretty interesting guy and probably not worth firing even if you don't like one of his …

I agree with the first half of this comment, but I don't follow you here: "Until there is an element of randomness fueled by context, they aren't creating anything new. That's wher…

Unicode Technical Report #51, which is where Emoji are laid out, talks a bit about the current thinking of the committees on this: > The longer-term goal for implementations should…

The matrix has nice features like flexible dates on a multi-leg trip that Google Flights doesn't offer.

I really like your Hidden Unit Zoo here http://colinmorris.github.io/rbm/zoo/ as a window into what this thing is actually "thinking" about. The "top matches" for a given hidden un…

The possibilities for how language will work in the future are really exciting and interesting! We made the Minuum keyboard, too, which also explores how machine learning assistanc…

Well those are sort of equivalent. But yeah, we use cross-entropy between the projected output and the target emoji distribution as our objective to minimize. And yes, we do the t-…

Not officially, although people have started reverse-engineering the website ;). We can get an actually supported one up officially if there's interest. Email me at xavier@whirlsca…

Well you can search in Dango, too ;) But yeah our main focus is suggestions. You can use Dango concurrently with the normal emoji keyboard, of course! It can just sit there showing…

Yeah we'd need to do some more work. But this is similar to stickers and GIFs: there are many fewer examples for any given sticker or GIF, which is why we do transfer-learning appr…

Yeah so this is a legitimate concern. Of course sometimes it's fun to say "let's eat pizza :pizza_emoji:", but that's not hugely valuable. However, Dango's training data includes p…

So yeah: we can focus on vectors at different levels of the net and these are in some sense different semantic spaces. In the article I talk about a level immediately before it pro…

Yeah this is a real challenge with AI systems, they reflect both our worst and our best back at us, we're still struggling with the best way to deal with this. Although in this par…

We start supporting them as soon as they're available! Obviously we have a lot less training data early on but we can lean on some heuristics early on until it builds up. Unfortuna…

Thanks! I was tempted to go way more technical but we decided it would be fun to let more people get some intuitive grasp of these kinds of algorithms.

All over the web! For instance, over 20% of all tweets have emoji in them. Emoji are very popular in instagram comments, etc.

;)

Yes it can, language models can generate phrases that have not been seen before. Karpathy's RNN post is a pretty good intro to how that works http://karpathy.github.io/2015/05/21/r…

We use t-SNE for the projection! We do mention it somewhere in there. Could maybe be more clear The sequences of emoji we ended up glossing over here (difficult balance making thes…