Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @cezannecam
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @cezannecam
-
Prikvačeni tweet
Completed an implementation of a simple Capsule Network! You can take a look at the code, here: https://github.com/cezannec/capsule_net_pytorch …. The trained network has some cool traits, and I tried to replicate some experiments they did in the og paper, like feature visualization via reconstructionspic.twitter.com/ny9slxhXoZ
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I have been taking pictures of clouds for a while and I recently gathered a bunch of photos and used them to train a low-res GAN. Here are some cute fake-clouds for
#cloudtwitterpic.twitter.com/fKPaYree8c
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The blog post has some great visualizations such as this one, which shows a network, starting out with randomly-weighted connections then learning to strengthen important connections during training (thanks for the clarification
@Mitchnw)! https://mitchellnw.github.io/blog/2019/dnw/ pic.twitter.com/FNCmVZYXtiPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Very cool work on a neural net that can jointly learn the weights and *connections* between nodes in an NN during training! A simple update rule relates the "importance" of a node-node connection (wrt decreasing the training error) to a weight assigned to that connectionhttps://twitter.com/Mitchnw/status/1176173492426821639 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
On auditing as a tool to make AI systems more transparent and accountable to the populations they affect. The brilliant
@rajiinio discussed strategies for designing an actionable audit of facial recognition systems, taking inspiration from the social and information sciencespic.twitter.com/jpKBh50UyV
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The
#1619Project is devastating and affecting. I’m linking to the livestream in which historians and writers use objects and the creative imagination to tell the history and legacy of slavery. I’m learning much for the first time and will continue to learn https://timesevents.nytimes.com/1619NYC https://twitter.com/jazzedloon/status/1161695715636273153 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I'd be so curious to see how different video embeddings relate to one another in this embedding space
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
One more detail: the system learns embeddings for each video (in a style similar to learned, word embeddings) based on a number of features including “freshness” or the time a video was uploaded. A sequence of these embeddings = your user watch history
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
After reading about these rankings being biased towards extreme results, I wanted to see how the "watch time" optimization worked. The linked paper is "Deep Neural Networks for YouTube Recommendations" [Covington, Adams, Sargin (2016)]
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Reading the paper on the YouTube recommendation system; it's made up of 2 neural nets: one for video-candidate generation and one for ranking those videos. The ranking net predicts your "watch time" for each candidate and shows you the highest-ranked vids https://storage.googleapis.com/pub-tools-public-publication-data/pdf/45530.pdf …pic.twitter.com/QQvLK8B39L
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"YouTube’s recommendation system is engineered to maximize watchtime, among other factors... As the system suggests more provocative videos to keep users watching, it can direct them toward extreme content they might otherwise never find." -https://www.nytimes.com/2019/08/11/world/americas/youtube-brazil.html …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
On YouTube’s recommendation system & the spread of misinformation and radicalization. Paraphrasing: The emotions that draw people into videos (which YT's system learns to surface and highly-recommend) are often central features of conspiracy theories, and of right-wing extremism.https://twitter.com/Max_Fisher/status/1160950447156473856 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
A good lunch-time read about a PizzaGAN! Using a structure similar to a CycleGAN, researchers trained models to add and remove pizza toppings. They show that the PizzaGAN can learn to segment pizza toppings, and remove them (via inpainting) http://pizzagan.csail.mit.edu/#Results pic.twitter.com/19FMO9zqJ6
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Cezanne Camacho proslijedio/la je Tweet
@YaoQinUCSD ,@colinraffel ,@sabour_sara , Gary Cottrell,@geoffreyhinton and I have released a full version of our workshop paper on capsule networks and adversarial attack detection! Check it out, or read this thread if you are busy :) 1/7 https://arxiv.org/pdf/1907.02957.pdf …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
A great tool for exploring open source repositories,
@github recently released a "jump to definition" feature which allows you to hover over a function, and jump to its original definition within that same repo! https://help.github.com/en/articles/navigating-code-on-github …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I was thinking that fitting to a dataset average does build in bias. For example: would a general, diagnostic classifier perform better on people of certain genders or age groups? Yes, and it depends on the data source, which cannot be directly investigated if it’s private
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The goal of techniques like differential privacy is to formalize this idea and develop methods for 1. quantifying information leakage and 2. proving that a model is not leaking too much of one individual's information (so, someone cannot reconstruct an individual’s data)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The most helpful patterns for a classifier (that generalizes well) may be thought of as *general truths* that are buried in private, individual data
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Imagine training a model to do cancer recognition. This ML model aims to learn information that is consistent across individuals and can help identify any new cases of cancer; in fact, we explicitly do *not* want our model to overfit to any one piece of data
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Specifically, we often want to train an ML model to generalize well to new tasks, which means we want the model to recognize general patterns and not any patterns unique to an individual person (and this personal data should be private!)
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.