jay_mlr

Jay. Machine Learning Researcher. Non-authoritative source of ML quips and the occasional useful tweet.

[jay_mlr @jay_mlr]

Love PAC

[jay_mlr @jay_mlr]

Punk ROC curve

[jay_mlr @jay_mlr]

BarRNN

[jay_mlr @jay_mlr]

What are you gating for?

[jay_mlr @jay_mlr]

It's all been done before - no parody required

[jay_mlr @jay_mlr]

Any weight you want it, that's the way we'll anneal it- @BenjoLondon

[jay_mlr @jay_mlr]

Convolve Together

[jay_mlr @jay_mlr]

We're coming up with Imposterior parody titles

[jay_mlr @jay_mlr]

@berty38 Force all of them to speak only in cockney accents for the remainder of the election, all problems solved.

[jay_mlr @jay_mlr]

“Try to find a universal definition for a forest. Tree-cky!” -- @pascalhitzler speaking at KIT

[jay_mlr @jay_mlr]

@berty38 You know me - always be looking for a pun. Does microblogging mean to and too are substitutable?

[jay_mlr @jay_mlr]

I wish every research paper had a blog post like this with clear & simple explanations: https://t.co/cahVLBeXsd

[Bert Huang 🐥 @berty38]

Upcoming AISTATS paper http://t.co/DKzSWmJSo1

[jay_mlr @jay_mlr]

@berty38 Right, stick to 16 so you can do a March Madness bracket with them...

[jay_mlr @jay_mlr]

@stevebach @sanapants @proteius Is the instructor particularly good? Are classes how you learn best? Will you devote ample time to it?

[jay_mlr @jay_mlr]

All exchangeable variables are alike; each conditionally independent variable is conditioned in its own way. Reading: http://t.co/ht53oMqA6Y

[jay_mlr @jay_mlr]

Interested in how Linked Data and Info Extraction can work together? @LD4IE2014 workshop posted their CFP http://t.co/KyfWuv1YaZ #ISWC

[jay_mlr @jay_mlr]

Can MLNs learn how to make tea? Seems possible from today's reading group: http://t.co/IH3dCXM798

[jay_mlr @jay_mlr]

“You can order by truth value, which is a partial ordering, but it’s very shallow since the values are 0 and 1. It’s not a very tall order."

[jay_mlr @jay_mlr]

Wry: “I’ve been working in this field for a long time. I was working on Big Data before it was big - back when it was just data.” #s4bd13