Twitter
Black mirror...

None of the faces next to mine are real.
from twitter_favs
yesterday
Twitter
Program inverts a GAN from an image to find a latent vector and slowly explores the space using optimal transport.…
from twitter_favs
yesterday
Twitter
Imagine yourself as someone else with a neural network. Likeness of used w/permission.…
from twitter_favs
yesterday
Twitter
Hi! Are you back in DC?? (Saw you're organizing Vue Vixens DC, and speaking of meetups: :)
from twitter
3 days ago
Untitled (https://www.meetup.com/DC-Hack-and-Tell/events/257283703/)
Join us this Thursday for Round 64: You to the Sixth! Looking forward to those hacks!
from twitter_favs
3 days ago
Manipulating and Measuring Model Interpretability
Despite a growing literature on creating interpretable machine learning methods, there have been few experimental studies of their effects on end users. We present a series of large-scale, randomized, pre-registered experiments in which participants were shown functionally identical models that varied only in two factors thought to influence interpretability: the number of input features and the model transparency (clear or black-box). Participants who were shown a clear model with a small number of features were better able to simulate the model’s predictions. However, contrary to what one might expect when manipulating interpretability, we found no significant difference in multiple measures of trust across conditions. Even more surprisingly, increased transparency hampered people’s ability to detect when a model has made a sizeable mistake. These findings emphasize the importance of studying how models are presented to people and empirically verifying that interpretable models achieve their intended effects on end users.
3 days ago
Twitter
The only day it goes really crazy is gardner day. (They’re around the porch area a lot!) It was rea…
from twitter_favs
6 days ago
Neural Networks for Automatic Target Recognition
by Michael W. Roth, Johns Hopkins APL

from 1990
7 days ago
(429) https://twitter.com/i/web/status/1082797578956296193
My baby girl went from barely being able to crawl to sitting up to trying to stand on her own at the side of her pl…
from twitter_favs
9 days ago
Twitter
If you mean "percent," write "%" - as in "Performance improved 10%, from 20% to 22%."

If you mean "percentage poin…
from twitter
9 days ago
Quaternion Recurrent Neural Networks
@metasemantic combining two things you like:
10 days ago
Twitter
Gaussian Processes
Gaussian Processes are Not so Fancy

A Visual Exploration of Gaussian Pr…
from twitter_favs
10 days ago
Twitter
"It is precisely our commitment to democratic principles that puts us at an asymmetric disadvantage against an adve…
from twitter
13 days ago
Twitter
this is a neat elucidating perspective that takes 10 mins to read! Gaussian processes are a k-nearest neighbors + l…
from twitter_favs
14 days ago
Twitter
Gaussian Processes are Not So Fancy
from twitter_favs
14 days ago
Twitter
2018 was a great year, creating a record 239 new modules for DeltaMath! Hoping to make 2019 even more productive, s…
from twitter_favs
15 days ago
The Expectant Father and so on
"The Expectant Father and so on" live and learn
from twitter
17 days ago
Twitter
It's been a goal of mine to get a sequence published in OEIS. Just saw this morning that D…
from twitter_favs
17 days ago
Untitled (https://gfycat.com/TotalImpureCrane)
It's been a goal of mine to get a sequence published in OEIS. Just saw this morning that D…
from twitter_favs
17 days ago
Untitled (https://www.dreamsongs.com/Files/LispGoodNewsBadNews.pdf)
the worse-is-better paper: “Unix and C are the ultimate computer viruses.” ... “continuatio…
from twitter
19 days ago
Twitter
the worse-is-better paper: “Unix and C are the ultimate computer viruses.” ... “continuatio…
from twitter
19 days ago
Twitter
“The Structure of a Programming Language Revolution” This Richard Gabriel guy is good! Fun…
from twitter
20 days ago
The structure of a programming language revolution
“The Structure of a Programming Language Revolution” This Richard Gabriel guy is good! Fun…
20 days ago
The Equation of a Plane
"The Equation of a Plane" (Math story-time, walking down memory lane...)
from twitter
20 days ago
Twitter
"Implementation and Use of the PLT Scheme Web Server" In which functional programmers fight…
from twitter
20 days ago
Twitter
* Land of Lisp
* How To Invent Everything
* Brain Rules for Baby…
from twitter
20 days ago
Twitter
* Worm
* The Coming Jobs War
* Scarcity …
from twitter
20 days ago
Twitter
Books I read in 2018:

* The Man in the High Castle
* Boomerang …
from twitter
20 days ago
The Man in the High Castle
Books I read in 2018:

* The Man in the High Castle
* Boomerang …
from twitter
20 days ago
Boomerang by Michael Lewis
Books I read in 2018:

* The Man in the High Castle
* Boomerang …
from twitter
20 days ago
Twitter
It works by acting as a regularizer.
from twitter_favs
24 days ago
Twitter
This trend of ML tools that don’t even tell you which algorithm you’re applying is the most awful manifestation of…
from twitter_favs
25 days ago
Twitter
Just a reminder that the CR passed the Senate unanimously and would have passed the House with a huge vote but Paul…
from twitter_favs
27 days ago
Deep contextualized word representations
ELMo: Embeddings from Language Models
27 days ago
Twitter
Happy to share that I will be joining in January, as a Staff ML Engineer on their Recommendations team…
from twitter_favs
27 days ago
Twitter
We just passed a bill that requires all data the govt collects (that isn’t secret or private) to be machine readabl…
from twitter_favs
29 days ago
Twitter
What’s the best Creative Commons license for dance moves so we can all avoid further Fortnite dance litigation. Als…
from twitter_favs
4 weeks ago
Twitter
Hey! What are you doing the first half of 2019? How about Hack and Tell, now scheduled monthly through June?…
from twitter_favs
4 weeks ago
Twitter
Thanks Aaron! Hope you are doing well. I will check it out.…
from twitter_favs
4 weeks ago
Twitter
The determinant of a matrix is how much the matrix expands or contracts space. More precisely: it's the volume of t…
from twitter_favs
4 weeks ago
Twitter
. shows his music/light hack, soon to be out in public in Virginia!
from twitter
5 weeks ago
Twitter
News for me: I'm leaving at the end of this month, and going over to the first branch to work for Congress! I'…
from twitter_favs
5 weeks ago
Twitter
Spectacular lineup for tonight! Lots of hardware and data science hacks... It’s going to be fun!…
from twitter_favs
5 weeks ago
A Bayesian Perspective on Generalization and Stochastic Gradient Descent
Samuel L. Smith and Quoc V. Le

answers issues of learning random labels?
5 weeks ago
Twitter
A Bayesian Perspective on Generalization and Stochastic Gradient Descent – Google AI
from twitter_favs
5 weeks ago
A Bayesian Perspective on Generalization and Stochastic Gradient Descent – Google AI
A Bayesian Perspective on Generalization and Stochastic Gradient Descent – Google AI
from twitter_favs
5 weeks ago
Brain Rules for Baby
"Brain Rules for Baby" To be a good parent, be a good person.
from twitter
5 weeks ago
« earlier      
book cli linux python ssh x

Copy this bookmark:



description:


tags: