Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @heghbalz
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @heghbalz
-
Prikvačeni tweet
#MLTwitter, Do you know a sponsor for an ML research project that can offer ~50 GPUs for couple of months? Research done at the University, is open source, and we have a convincing proposal. Open to colabs in case needed. Can you share this tweet plz?#RetweeetPlease#RETWETT#rtPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hamid EBZD proslijedio/la je Tweet
"How to do machine learning efficiently". There's so much to love about this wonderful article. https://medium.com/hackernoon/doing-machine-learning-efficiently-8ba9d9bc679d …pic.twitter.com/n6otKKP3gJ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
NEW: Research paper by Florian Henkel, Stefan Balke, Matthias Dorfer and Gerhard Widmer, “Score Following as a Multi-Modal Reinforcement Learning Problem”, using raw score images as input.https://transactions.ismir.net/articles/10.5334/tismir.31/ …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Does anyone know a simple, *fast* way to display a numpy array as pixels, e.g. for watching cellular automata in real time? (I usually use pygame but it has some weird issues on retina displays, so I'm wondering if there's a better option.)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Wow, I also didn't know about this. I'll try it out next time I'm presenting! "It uses your computer’s microphone to detect your spoken presentation, then transcribes—in real time—what you say as captions on the slides you’re presenting. " (cont)https://twitter.com/edchi/status/1224561613736415232 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Adding an independent Gaussian variable is the same as doing a heat diffusion on the density. https://en.wikipedia.org/wiki/Convolution_of_probability_distributions …pic.twitter.com/mSnqZUfRVr
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Our white paper from
@ipam_ucla deep fakery workshop is out! It was an amazing experience to collaborate with such a diverse team from legal, social, and computer science backgrounds. The compilation of our observations and our prospective research agenda is below.#deepfakeshttps://twitter.com/ipam_ucla/status/1214759738325422080 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Alright. Inspired by this tweet, I decided to read all relevant
#Coronavirus preprints (about 30 in all). Here's what I've found, a thread. 1/15https://twitter.com/ryneches/status/1223439143503482880 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hamid EBZD proslijedio/la je Tweet
Play against my first home made
#ReinforcementLearning game agent (https://zackakil.github.io/deep-tic-tac-toe/ …) I built using@TensorFlow +#Keras +#TensorFlowJS +@vuejs! Genuinely amazed that it seems to work
Big thanks my teachers @Sentdex ,@aureliengeron,@gusthema, and@polonglin

pic.twitter.com/DRACkNmnVYHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
@FeiziSoheil speaking about adversarial attacks for invertible generative models at#ita2020pic.twitter.com/YwF7tS2zNO
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Neural Tangent Kernels (NTK) are a way of understanding neural networks in a certain domain (in the limit of N ->\infty, W0 not ~0). It is beautiful. And somewhat counterintuitive. Here are two nice write-ups aimed at explaining: https://rajatvd.github.io/NTK/ ,http://www.offconvex.org/2019/10/03/NTK/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
This is indispensable for quite a few of us! Thanks,
@NPRougier for this nifty cheatsheet!https://twitter.com/njgoldbaum/status/1160609675471196161 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
what is
#tractable#probabilistic#inference? and when a probabilistic model can be deemed tractable? we are brought to divide classes of models into#tractable VS#intractable ones. A dualism that can be somehow misleading. 1/3#probabilistic#circuits#PCs#AAAI20@RealAAAIpic.twitter.com/o4pGkHsbW7
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hamid EBZD proslijedio/la je Tweet
Allowing requests for experiments within a one week window favors labs with big compute, and destroys the work-life balance of the people having to run the actual calculations. (You might not be able to start experiments on the _weekend_ the reviews appear, if you have kids.)
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
99 smartphones are transported in a handcart to generate virtual traffic jam in Google Maps. Through this activity, it is possible to turn a green street red which has an impact in the physical world by navigating cars on another route!
#googlemapshacks http://www.simonweckert.com/googlemapshacks.html …pic.twitter.com/6KcMm1XgAF
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
My attempt for our book at explaining the difficulty of training deep networks, for folks not familiar with math beyond high school. Any suggestions to make this clearer or simpler (*not* more mathematically rigorous)?pic.twitter.com/GD0KgpXQY1
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
Curriculum for Reinforcement Learning "Learning is probably the best superpower we humans have."
@lilianweng explores four types of curricula that have been used to help RL models learn to solve complicated tasks. https://lilianweng.github.io/lil-log/2020/01/29/curriculum-for-reinforcement-learning.html …pic.twitter.com/UTWHt9l3ng
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hamid EBZD proslijedio/la je Tweet
The
#CVPR2020 program chairs answered my inquiry about including requested ablations in the rebuttal. Here’s their official response. Feel free to comment below. Source: http://www.facebook.com/460123958071182/posts/627453564671553 … https://twitter.com/CSProfKGD/status/1223668960979234816 …pic.twitter.com/1qSOKFlw9J
Hvala. 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.

@ JKU