Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @voidtarget
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @voidtarget
-
Prikvačeni tweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Giovanni Petrantoni proslijedio/la je Tweet
Wow.... and while using Windows 2000 by the looks of it.https://twitter.com/SamBendett/status/1222896509919744004 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This really shows that users experience and ease of use is indeed above all even in this field. Lots of lessons learned for new frameworks too! Also shows that users really don’t care about technical details and internal stuff (where I see other frameworks honestly superior).https://twitter.com/ctnzr/status/1222940800461312001 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Wow, I was looking for a, even local, hackmd like replacement! Had no idea you were working on this as well!
@CasualEffectshttps://twitter.com/casualeffects/status/1221883785987395584 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you don’t know it already comby by
@rvtond is probably the best tool for code refactor you need. It saved me many hours of regex/(x paid tool) etc...https://github.com/comby-tools/comby/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
No BLAS? No problem. This is the first post of the series implementing various algorithms in ANSI C with 0 dependencies for the DYI people. Stay tuned. Here' s #1: A 2-layer MLP getting beating OpenBLAS' performance and getting over 95 % in under 5s.https://github.com/krocki/MLP-C
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
One of the most important debugging technique of my life - numerical gradient check. This is a short intro and working piece of some for two models sharing the same grad-check scaffolding: a classifier and an Autoencoder. Pure Numpy! https://github.com/krocki/gradcheck …pic.twitter.com/3xZriqxbDP
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
It's easy to ridicule overconfidence. And indeed, it has its disadvantages. But it's just what you need if you want to take on a problem most rational people would conclude was too hard. Fools dare where angels fear to tread, and sometimes they win.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alternatively
@ManjaroLinux could be even a better choice due to better user experience/tools while being still an Arch Linux core.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
Differentiable Digital Signal Processing (DDSP)! Fusing classic interpretable DSP with neural networks.
Blog: http://magenta.tensorflow.org/ddsp
Examples: https://g.co/magenta/ddsp-examples …
Colab: http://g.co/magenta/ddsp-demo …
Code: http://github.com/magenta/ddsp
Paper: http://g.co/magenta/ddsp-paper …
1/pic.twitter.com/SlxLUOUC6k
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The beautiful thing about
#creativity is that sometimes it even makes ignorance about something worth it. Too much information, knowledge and theories often make us counterproductive. Resist bad influences! Educate yourself, dig into things, but most of all create; experiment!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Nice article! I'm glad to know I'm not a heretic. I know so many people that should read this :)https://twitter.com/dan_abramov/status/1216110520891334660 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lesson learned while making
@NimTorch Garbage collected languages likely fail at#MachineLearning#HPC#DataScience for mainly 2 reasons: 1. The GC will be unaware of GPU memory, a tensor of GBs will be just few bytes for the GC 2. GCs make coroutines nearly impossibleHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
Recent language models like BERT and ERNIE rely on trendy layers based on transformer networks and require lots of compute. Deep learning researcher
@Smerity shows these layers and enormous GPUs may not be necessary: http://bit.ly/2QZXxWV pic.twitter.com/d03D7A7CAD
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Giovanni Petrantoni proslijedio/la je Tweet
About it: https://medium.com/@lucaspereira0612/solving-xor-with-a-single-perceptron-34539f395182 … and especially: http://www.uncini.com/research_activity/pdf/035_ijcnn92.pdf … . The recent XOR hype has been misunderstood and (wrongly) readapted to the ML world (in fact people try to read -wrongly- those findings with tools they are familiar with, like gaussian functions, etc).
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Probably I will keep it in Nim for now, if possible, and just work on a better language agnostic high level interface!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Wondering if I should rewrite my unreleased
#neuroevolution framework in C++ or keep it in Nim (assuming ARC is stable)…@NimTorch proved that there is very little interest in such libraries written in not so popular languages sadly
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Really 1 ANN neuron XOR solving, evolved using GA (solved at generation 0… thanks to random number generator god) Apparently it found that a “Gaussian” activation was the key, just like the recent biological neuron paper hinted basically afaik.
@kairosdojo@bensprecherpic.twitter.com/bFHqeLcHiK
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
AdderNet and DeepShift... could make tensor cores (in deep shift) obsolete! (btw, they won't last long one way or another) https://arxiv.org/abs/1905.13298 https://arxiv.org/abs/1912.13200
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Fift language https://github.com/ton-blockchain/ton/tree/master/crypto/fift … By
@telegram's TON blockchain project Pretty cool to see a modern#Forth inspired language written in C++ Hidden gem there is a#scheme/#lisp interpreter written in Fift too!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
More about spinlocks being bad ( and the previous article I linked too ! ), by Linus himself https://www.realworldtech.com/forum/?threadid=189711&curpostid=189723 …
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.
