2625
Twitter
4 hours of baby play in 2 minutes
from twitter_favs
4 days ago
Twitter
Almond milk is milk.

I'm surprised how angry I am about this, but the claim that almond milk is some sort of new i…
from twitter_favs
18 days ago
Twitter
This is... deeply unsettling.

Source:
from twitter_favs
21 days ago
Twitter
I think about this suggestion from Scott a lot. I kind of think every CS undergrad should be required to i…
from twitter_favs
21 days ago
Twitter
Phil Blunsom had some good results pre-seq2seq in 2013/14 using addition of embeddings as an encoder and a…
from twitter_favs
23 days ago
Twitter
messing around visualizing d-separation from bayes nets! each variable is conditionally independent of non-descenda…
from twitter_favs
26 days ago
Twitter
Rich based in : welcome to CSV-stat! Or the JSON-stat Comma-Separated Values format (.JSV).

Supporte…
from twitter_favs
29 days ago
Twitter
"… a generic name demonstrates an abdication of responsibility by the designer."
from twitter_favs
4 weeks ago
Twitter
it would've been truer to the spirit to _remove_ features
from twitter_favs
4 weeks ago
Twitter
I do'nt care what Kids at School call me because they are all Disgusting Fake Losers and my Real Friends go to a di…
from twitter_favs
4 weeks ago
Twitter
Dalí: Surrealism is DESTRUCTIVE, but it DESTROYS only what it considers to be SHACKLES limiting our VISION.
Varo: I…
from twitter_favs
5 weeks ago
Twitter
from the furby source code dump
from twitter_favs
5 weeks ago
Twitter
One of my favorite Python 3 builtins is functools.lru_cache(): with a simple decorator, repeated function calls bec…
from twitter_favs
6 weeks ago
Twitter
aaargh the "When recurrent models don't need to be recurrent" paper is so frustrating!

On the one hand it presents…
from twitter_favs
6 weeks ago
Twitter
"Then, with one hand, tap the side of the microscope stage to jolt the needle through the cuticle."

Like physical…
from twitter_favs
7 weeks ago
Twitter
I love this. Thanks for all your work on spaCy and helping us all navigate the world of NLP…
from twitter_favs
7 weeks ago
Twitter
Plan 9 and Dynamicland both dramatically simplify application code by providing _common ways to list and act on obj…
from twitter_favs
9 weeks ago
Twitter
Holy. Shit. Expressive, interesting, and lengthy piano music generations. I genuinely got goosebumps listening to t…
from twitter_favs
10 weeks ago
Twitter
Exciting news: Brain expands to Amsterdam 🚲🚣🌳 Looking forward to working on core AI challenges with…
from twitter_favs
10 weeks ago
Twitter
Well here goes. Our ICML Debates paper is live: "Troubling Trends in Machine Learning Scholarship". If anyone needs…
from twitter_favs
10 weeks ago
Twitter
Wonder how well would the latest segmentation and detection approaches (DeepLabV3+, FasterRCNN) perform on street f…
from twitter_favs
11 weeks ago
[1805.08498] Implicit Reparameterization Gradients
With we recently put out a paper on Implicit reparameterisation gradients (). And…
from twitter_favs
11 weeks ago
Twitter
With we recently put out a paper on Implicit reparameterisation gradients (). And…
from twitter_favs
11 weeks ago
Twitter
"Lines that are parallel meet at infinity!"
Euclid repeatedly, heatedly urged.
But when he die…
from twitter_favs
12 weeks ago
Twitter
Neural networks are just ways of transforming high dimensional things into low dimensions such that you can apply a…
from twitter_favs
12 weeks ago
Twitter
This is by far the nerdiest t-shirt I’ve ever had (and I have a lot). Thanks
from twitter_favs
12 weeks ago
Twitter
App ‘Archeologica’ wint app wedstrijd provincie Zuid-Holland
from twitter_favs
12 weeks ago
Twitter
Giddy at an experimental new feature in Pages: add annotations and marginalia in digital ink and they're anchored t…
from twitter_favs
12 weeks ago
What are good algorithms to generate borders / state areas on 2d star maps? - Game Development Stack Exchange
I sometimes spend hours on interesting stackoverflow questions. This morning I looked at an…
from twitter_favs
june 2018
Twitter
I sometimes spend hours on interesting stackoverflow questions. This morning I looked at an…
from twitter_favs
june 2018
Twitter
The recent paper out from Google, "Scalable and accurate deep learning with electronic health records", has an nota…
from twitter_favs
june 2018
Twitter
Neural ODEs: Instead of updating hiddens layers by layer, we specify their derivative wrt depth with a neural netwo…
from twitter_favs
june 2018
Twitter
Excited to release ! DIVE makes data exploration more accessible with semi-automated data vi…
from twitter_favs
june 2018
DIVE
Excited to release ! DIVE makes data exploration more accessible with semi-automated data vi…
from twitter_favs
june 2018
Twitter
Keynote meets LaTeX and I love it: Apple Keynote now allows you to enter (and edit!) equations in LaTeX notation.…
from twitter_favs
june 2018
Twitter
Congrats to winning the Student Research Competition with his work on
from twitter_favs
june 2018
Twitter
We just opened another vacancy, for a PhD student to work on dataset search. Come and join us to work on AI & IR, t…
from twitter_favs
june 2018
Twitter
Aha, the word I'm looking for is apparently "georeferencing", and this looks very much like what I want:…
from twitter_favs
june 2018
Twitter
Object-avoiding paths , and a card which shows a live visualization of the algorithm. Thanks for the A…
from twitter_favs
june 2018
Twitter
Question out of ignorance: If the models like the new model becomes defacto, doesn’t this perpetuate blindl…
from twitter_favs
june 2018
Twitter
did terminology move and i didn't notice? do you consider language modeling (training a probabilistic model p(w1 w2…
from twitter_favs
june 2018
Twitter
NeuralCoref v3.0 is out✨!
- up to 100x faster than v2.0 (thanks Cython) 🚀
- Integrated in spaCy models and pipeline…
from twitter_favs
june 2018
Twitter
Let's talk about macOS Mojave. This new version of the Mac operating system is emblematic of Apple's strip-mining C…
from twitter_favs
june 2018
Twitter
Some under-appreciated reasons why CPU is strong for many NLP tasks:
1. Batch sizes often need to be small, especia…
from twitter_favs
may 2018
Twitter
A few months ago tweeted that radiologists were on the verge of being obsolete because AI:…
from twitter_favs
may 2018
Twitter
Computational Design of Transforming Pop-up Books
from twitter_favs
may 2018
List of English terms of venery, by animal - Wikipedia
has an amazing list of names for groups of animals . I’m off to go watch a “padd…
from twitter_favs
march 2018
(429) https://twitter.com/i/web/status/976393002284408833
has an amazing list of names for groups of animals . I’m off to go watch a “padd…
from twitter_favs
march 2018
Twitter
So...I just read the "Machine Theory of Mind" paper () from DeepMind. I actually like the i…
from twitter_favs
march 2018
[1802.07740] Machine Theory of Mind
So...I just read the "Machine Theory of Mind" paper () from DeepMind. I actually like the i…
from twitter_favs
march 2018
Twitter
If this is due to machine learning, it is the most clear-cut case yet of optimizing the wrong objective. I'll bet i…
from twitter_favs
march 2018
Twitter
We don’t know how to ask the right question.
from twitter_favs
january 2018
Twitter
Ok folks, you have failed me for not telling me I can move a process to a screen session

1.…
from twitter_favs
december 2017
Untitled (https://www.linkedin.com/pulse/move-running-process-screen-bruce-werdschinski/)
Ok folks, you have failed me for not telling me I can move a process to a screen session

1.…
from twitter_favs
december 2017
Dynamicland
★ Dynamicland: incubating a humane dynamic medium
from twitter_favs
december 2017
Twitter
★ Dynamicland: incubating a humane dynamic medium
from twitter_favs
december 2017
Twitter
When botanist Richard Deakin examined Rome’s Colosseum in the 1850s, he found 420 species of plant growing in the r…
from twitter_favs
november 2017
Twitter
Time-Contrastive Networks: Self-Supervised Learning from Video: clever use of the triplet loss on multiple viewpoin…
from twitter_favs
november 2017
Twitter
Published model vs reimplementation as baseline.
from twitter_favs
october 2017
Twitter
Went to a museum armed with Face App to brighten up a lot of the sombre looks on the paintings and sculptures. The…
from twitter_favs
may 2017
Twitter
After 3 years of hacking the Dat white paper draft is ready to read
from twitter_favs
may 2017
docs/papers at master · datproject/docs · GitHub
After 3 years of hacking the Dat white paper draft is ready to read
from twitter_favs
may 2017
Twitter
110k+ story plots from English Wikipedia for your (neural net’s) reading pleasure

(plus co…
from twitter_favs
april 2017
« earlier      
-textbooks -to-read ai_history data_integration deep_learning information_extraction linked_data msc_thesis natural_language_inference paper relation_factorization structured_prediction tidy_tables wordvectors

Copy this bookmark:



description:


tags: