Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @tataudat
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @tataudat
-
dat proslijedio/la je Tweet
Behold the Datasaurus Dozen. New video featuring
@JustinMatejka and a mention of@donttrythis's book club. https://www.youtube.com/watch?v=iwzzv1biHv8 …pic.twitter.com/EaRbuMJCHlHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
dat proslijedio/la je Tweet
*Grumpy Chris:* One of my biggest research gripes is people boiling the world down into a couple summary statistic numbers and feeling like that somehow made things more rigorous.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
In 2020, we will celebrate that many of the basic ideas behind the Deep Learning Revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" 1990-1991:http://people.idsia.ch/~juergen/deep-learning-miraculous-year-1990-1991.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
The Sunray solved *A* problem. It had things it did better than the alternatives that existed at the time. It was made with *A* user in mind, even if that user (Sun Microsystems employees) were the same people making the Sunray. There was *someone*— me, in 2004— it was great for.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Hey
@numberphile , I solved your Cat and Mouse game (https://www.youtube.com/watch?v=vF_-ob9vseM …) using Reinforcement Learning! https://www.declanoller.com/2019/08/30/solving-numberphiles-cat-and-mouse-puzzle-using-the-ddpg-and-a2c-reinforcement-learning-algorithms/ …pic.twitter.com/zHMeBwe54vHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Series: the 20 most tactically interesting teams of the 2010s. One per week on
@TheAthleticUK.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Some of the smartest people I know are leaving AI research for engineering/neuroscience. Their reasons? 1. We need to understand how humans learn to teach machines to learn. 2. Research should be hypothesis -> experiments, but AI research rn is experiments -> justifying results.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je TweetPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
dat proslijedio/la je Tweet
The equal sign forms the bedrock of mathematics. Some mathematicians think it needs to be replaced. https://www.quantamagazine.org/with-category-theory-mathematics-escapes-from-equality-20191010/ …pic.twitter.com/GIJov1EG0z
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Often times, when you'd like to find out best language practices, you go to the standard library. Weirdly enough, with Rust, I mostly see a bunch of "unsafe" there. Even for something as simple as linked list. Anyone can clarify why?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
why are all the violin concertos in the key of D? Full video
https://youtu.be/OXLnDvwD0v0 pic.twitter.com/2BY7s1qakaHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
dat proslijedio/la je Tweet
Right-- the goal of default kwargs is not to reduce the amount of typing people do, it's to run the way you think it does based on the name. People get this twisted because it's similar, but you can run through hypothetical code examples to see this.https://ryxcommar.com/2019/08/30/scikit-learns-defaults-are-wrong/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
By default, logistic regression in scikit-learn runs w L2 regularization on and defaulting to magic number C=1.0. How many millions of ML/stats/data-mining papers have been written by authors who didn't report (& honestly didn't think they were) using regularization?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective Review paper that aims to shed lights on the importance of dynamics and optimal control when developing deep learning theory. https://arxiv.org/abs/1908.10920 pic.twitter.com/PeBBGhvQ2r
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Facebook scans system libraries from their Android app user’s phone in the background and uploads them to their server This is called "Global Library Collector" at Facebook, known as "GLC" in app’s code It periodically uploads metadata of system libraries to the serverpic.twitter.com/olwk1BPMoQ
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Looking back over the year, the one paper that gave me the best "aha" moment was... Reconciling Modern Machine Learning and the Bias-Variance Tradeoff: https://arxiv.org/abs/1812.11118 The "bias-variance" you knew was just the first piece of the story!pic.twitter.com/J24b0W8LDR
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
today i learned that Python rounds `float` values by converting them to a string with snprintf and then back via strtod, and now i'm sad. https://github.com/python/cpython/blob/master/Objects/floatobject.c#L965-L972 …pic.twitter.com/tOJPkFSw9j
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
dat proslijedio/la je Tweet
Less: ways of computing p-values, hypothesis testing, fuss over whether to divide by n or n-1 in sample var, tedious calculations More: thinking about data quality, sampling, likelihood, bias-variance tradeoff, simulation, visualization, discussion of common misconceptions
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.
Meet our