Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @advadnoun
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @advadnoun
-
I made a site! Here's a little post on cooperative communication networkshttps://rynmurdock.github.io/2020/02/05/CCN.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Examples of the output of agents that have essentially solved sending 10,000 classes with 64*64 pixels each against an agent adding noise. 10,000 classes with 4096 pixels is nothing.pic.twitter.com/7qKRbc7eNq
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
I need to do a curve/heatmap of various levels of noise compared to various image resolutions for communicating images. NN parameters may be a factor, but I figure the image dimensions are the bottleneck
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
And it isn't *just* initialization: if you've been following this project, you know that when noise is added instead of interference from an adversary, the images for each class closely converge between the 2 networks!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
By way of example, you can probably tell which two of these are from one NN and which other two are from another.pic.twitter.com/B2Gbrm9Did
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I don't know if I mentioned this before, but when trained with an adversarial agent adding interference instead of random noise being used, two communicating neural networks will develop their own "accents."
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Removing the embedding that projects from the number of categories to one image channel and instead relying only on AdaIN provides very straight-edged results!pic.twitter.com/r7jxvIiCmJ
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Using adaptive instance normalization a la StyleGAN in a CCN with adversarial interference to generate larger images representing many more classes! Here're some cherry-picked, early outputs.pic.twitter.com/gmgDUOJbQ9
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Interesting results with more pixels and more classes in this CCN...pic.twitter.com/dliNmpnyNs
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
What's really exciting is having an animation from the CCN-CPPN!pic.twitter.com/7iVjc3mlBD
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If anyone wants code for this process, I can make a lil' example colab notebook.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The rbf should have as many spaced-apart gaussians as you have categories, and now you've expanded your variable to be the same shape as if you had one-hot encoded it... but it will be as if you had some contribution from each embedding matrix that your number is near!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Here's the plan: you want to generate linearly spaced numbers from 0 to however many categories you have. Each one will become a frame in your animation. You then use a radial basis function to essentially slide gaussians over each linearly spaced number.
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.