Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @mahimapushkarna
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @mahimapushkarna
-
Prikvačeni tweet



The What-If Tool team wants to hear from you! Fill out this form to participate in an upcoming study to help us improve the #WhatIfTool !

https://docs.google.com/forms/d/e/1FAIpQLSc3eRjXj1aM2LSvaXX2dehyJq3ZSKMt0nBgvizW02OxJbkPFQ/viewform …
#MachineLearning#ExplainableAI#ModelUnderstanding#AI#interpretabilityHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you can ask a question that you hadn't already thought to ask of your model when using the
#whatiftool , we consider that a meaningful step in the right direction! My colleagues@bengiswex and@ZaldivarPhD unpack WIT x SHAPLEY values at#fat2020.https://twitter.com/bengiswex/status/1221481025039163392 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"Historically, minimalism tells us to focus on what doesn’t at first seem pleasant or beautiful and turn it into art instead of creating a worldview based only on what we already like."https://www.nytimes.com/2020/01/24/opinion/sunday/minimalism-definition-history.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
You can now search for datasets on Google: https://blog.google/products/search/discovering-millions-datasets-web/ … And, because one must test data tools with topics of importance, I looked for "chocolate+UK." Who knew that the top UK chocolate bars for all ages are Mars and Galaxy and Snickers? Congrats, Natasha Noy & team!pic.twitter.com/blawObKjOX
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
@a13xba spent last summer with@GoogleAI and PAIR exploring using DeepDream-style techniques on the BERT language architecture, as a model understanding probe. Check out the blog post for insights and code pointers: https://pair-code.github.io/interpretability/text-dream/blogpost/ …pic.twitter.com/8eStNgIijN
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Mahima Pushkarna proslijedio/la je Tweet
Poster today at
#NeurIPS2019 10:45am! #83 "Toward automatic conference base explanations"- work with my awesome intern@GhorbaniAmirata, and two awesome jamess - James Zou. And James Wexler@bengiswexPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
How does a neural net see depth in paintings? Does it "resolve" the depth depicted in these images in the same way we do? Read about depth predictions: https://pair-code.github.io/depth-maps-art-and-illusions/art_history_vis/blogpost/blogpost_1.html … PAIR project by
@EllenJiang2,@emilyrreif,@_beenkimpic.twitter.com/LDwQxP1kjK
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
What-If Tool 1.5 is now released, with full support for models that return feature-wise attributions! This accompanies the
@GCPcloud Explainable AI release. Let's dive in...#whatiftoolpic.twitter.com/Ag5GFzy6iN
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
#PAIRSymposium2019 just kicked off with a welcome note from@viegasf! Join us in this discussion about AI and#participatoryML via livestream
https://youtu.be/kZeSqzSObT4 pic.twitter.com/0W58DRGi0p – mjesto: Google UK
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
Want to learn how your ML models work under the hood?
@bengiswex and I have a new mini-series for you on the What-If Tool!https://youtu.be/qTUUwfG1vSsHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
Very pleased to release Alibi with
@arnaudvl3 and@seldon_io - an open source library for#MachineLearning model inspection and interpretation. Currently includes Anchors (@guestrin), contrastive explanations (@pinyuchenTW) and trust scores (@_beenkim):https://github.com/SeldonIO/alibiHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
Understanding UMAP--great interactive article by
@_coenen and@adamrpearce: https://pair-code.github.io/understanding-umap/ …pic.twitter.com/I1wkVV82GHHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you're at
#ieeevis today, come check out@bengiswex talk about what makes the What-if Tool from#PAIR@GoogleAI at Ballroom A in the session track "A tour of VAST"! Also, we have stickers!@wattenberg@viegasf@tolgab0pic.twitter.com/o9pQscOOdt
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning?
@cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry.#PyTorch#Tensorflowhttps://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
@philadao is hiring a UX designer. This is a great opportunity to help improve prosecutor transparency & work with great folks like@EverydayasOrenG! (@DesignGigs4Good,@cydharrell,@danachis can you help get the word out?)http://newton.newtonsoftware.com/career/JobIntroduction.action?clientId=8a7883c66439e9820164486786355d1c&id=8a78859e6d228d0f016d45ebbd9634c8&source= …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Is it weird to like all the posts in the thread?


Well it can't be helped, #WIT is now loaded with even neater capabilities :)https://twitter.com/bengiswex/status/1178750489879560192 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
+1 to this ENTIRE thread. Organizers & hosts - Pick up the phone and rehearse introductions if you must. Speakers, esp POCs - point audience to your bios in your slide annotations, and scope background info to your presentations.https://twitter.com/albanvillamil/status/1177620037294837761 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If fairness IRL is that elusive piece of the puzzle, ML Fairness is the one that just doesn't seem to fit!

@SRobTweets demystifies it a bit in her blog post!@bengiswex@viegasf@wattenberg@tolgab0https://twitter.com/SRobTweets/status/1176901945224761345 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Mahima Pushkarna proslijedio/la je Tweet
Such a fantastic resourcehttps://twitter.com/TheWJP/status/1176573931450355712 …
0:13Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
Human/AI Design
,
Converting Research to Tools
, Design Lead,

I've got a blog post for you!