@jay_mlr profile picture
jay_mlr @jay_mlr

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

Joined November 2013
  • Tweets 19
  • Following 128
  • Followers 162
Photos and videos
jay_mlr@jay_mlr
10 Dec 2017
Love PAC
1
jay_mlr@jay_mlr
10 Dec 2017
Punk ROC curve
jay_mlr@jay_mlr
10 Dec 2017
BarRNN
jay_mlr@jay_mlr
10 Dec 2017
What are you gating for?
jay_mlr@jay_mlr
10 Dec 2017
It's all been done before - no parody required
jay_mlr@jay_mlr
10 Dec 2017
Any weight you want it, that's the way we'll anneal it- @BenjoLondon
1
jay_mlr@jay_mlr
10 Dec 2017
Convolve Together
jay_mlr@jay_mlr
10 Dec 2017
We're coming up with Imposterior parody titles
1
jay_mlr@jay_mlr
7 Jul 2015
“Try to find a universal definition for a forest. Tree-cky!” -- @pascalhitzler speaking at KIT
1
5
jay_mlr@jay_mlr
6 May 2015
I wish every research paper had a blog post like this with clear & simple explanations: x.com/berty38/status/5953838…

Bert Huang 🐥@berty38
5 May 2015
Upcoming AISTATS paper ift.tt/1GWd0LO
1
3
jay_mlr@jay_mlr
20 May 2014
All exchangeable variables are alike; each conditionally independent variable is conditioned in its own way. Reading: arxiv.org/pdf/1405.0501.pdf
jay_mlr@jay_mlr
30 Apr 2014
Interested in how Linked Data and Info Extraction can work together? @LD4IE2014 workshop posted their CFP oak.dcs.shef.ac.uk/ld4ie2014… #ISWC
jay_mlr@jay_mlr
23 Apr 2014
Can MLNs learn how to make tea? Seems possible from today's reading group: ftp.cs.rochester.edu/u/kautz…
jay_mlr@jay_mlr
15 Nov 2013
“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
15 Nov 2013
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
Load more