Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @rharang
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @rharang
-
Prikvačeni tweet
Debugging deep learning models can be really tricky and frustrating, especially in the security space where a lot of the time you're not sure about ground truth labels, but here's a thread with some tricks I've picked up. Add your own if you've got them! 1/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
If you wondered why AV has false positives, take a look at this excel file: 1. Runs code automatically on opening 2. Uses native APIs that manipulate memory 3. Instantiates a COM object defined in a text string in a macro Benign. https://www.virustotal.com/gui/file/f08d2a2daa5aca5cf88db120198727f7965283c5aa6b4ea3d9452238250026f4/detection …pic.twitter.com/oOZIVw9gAS
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Rich Harang proslijedio/la je Tweet
Our latest paper,
Radioactive data: tracing through training, is now on arXiv. https://arxiv.org/abs/2002.00937
TL;DR: you can modify your data in an imperceptible way so that any model trained on it will have an identifiable mark. (1/7)pic.twitter.com/LOB8WRWowD
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Me: What absolute monster of a human being set their tab stop to *3* in this code? Also me: ...oh.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
How did I not know of this until now? https://pytorch.org/docs/stable/autograd.html#torch.autograd.detect_anomaly …pic.twitter.com/vgwvszgFEo
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
Monster-size models are *one* possible way to go about getting better results. Green AI proposes to pay attention not only to the optimization metric but the cost of getting at it. Smaller, faster, more data-efficient models are just better. http://arxiv.org/abs/1907.10597
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Today's "I need coffee moment": getting really mad that I couldn't import a module that was obviously in my conda environment, before realizing that it was *ipython* that wasn't in my conda env and I was running the system ipython (without the module I wanted).
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
The names of 100 prisoners are put in 100 boxes. One at a time, privately, each prisoner opens and closes 50 boxes. They are set free if *everyone* finds their own name. Strategy can be discussed beforehand, but otherwise there's no communication. What's the best strategy? 1/23
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
Elastic Weight Consolidation does indeed help our PE model avoid catastrophic forgetting! A little bit better than L2 regularization. I'm not convinced it's worth it for standard production releases (keep em' simple!), but it's very cool to see stuff like this work!pic.twitter.com/1YdsA8u4T8
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
This repo is full of amazing awesomeness. I don't know of anything else like it. Independent refactored carefully tested implementations of modern CNNshttps://twitter.com/wightmanr/status/1224178577593241602 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Rich Harang proslijedio/la je Tweet
Performance artist generates virtual traffic jams in Google Maps by pulling a wagon full of smartphones http://www.simonweckert.com/googlemapshacks.html …pic.twitter.com/m3bmQXvswI
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
There is a 2016 study "Can we still avoid automatic face detection?" by Cornell University which tests various camouflage techniques, including CV dazzle style makeup, against Facebook's face detection algo and the makeup is not able to fool the algo https://arxiv.org/pdf/1602.04504.pdf …pic.twitter.com/cjMuhCIOVM
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
"Giving BERT a calculator" https://arxiv.org/pdf/1909.00109.pdf … Big step in adding computational abilities to language models. Still no understanding but can certainly start to fool you. What happens if you "give BERT" thousand other similar abilities? cc
@GaryMarcusHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
If you need a name for a new malware, threat group operation or hack tool, check this Imgur gallery with 29 posters showing deities, monsters and heroes of different mythologies https://imgur.com/gallery/AlCZXEi pic.twitter.com/h2D93YJU6m
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
There is simply no way to safely test if a given cv dazzle pattern will fool the facial recognition algorithm before you go out wearing it.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Just imagine having to go to your client's HR department and say "Yeah... So turns out we just gave a 'highly recommended' rating to *literally anyone* with a Rothko print in frame, regardless of what they said. Sorry. That's multiple correlation testing for you, huh?"
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Whole new world of adversarial patches, though. "Is this person in front of the camera still Bob?" "FIIK but he's got a weird print on the wall behind him so I bet he's a hard worker!"
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We can't get facial *recognition* to work on people of color with acceptable success rates but yet we're forging ahead into cramming videos of applicants faces through piles of linear algebra to decide if they'd be a good hire? JFC. Enjoy your lawsuits. You deserve them.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rich Harang proslijedio/la je Tweet
Facebook for Android crashes in the recent build because I did not give it sufficient permission for location collectionpic.twitter.com/KOPbtMb2Fl
Prikaži ovu nitHvala. 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.