Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @alex_renda_
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @alex_renda_
-
Alex Renda proslijedio/la je Tweet
Tool predicts how fast code will run on a chip: Machine-learning system should enable developers to improve computing efficiency in a range of applications. http://mitsha.re/xTuF50xUbqJ pic.twitter.com/XDgpTDlKn8
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I'm thinking something along these lines, but I'm not sure that this is the best option: https://beagleboard.org/green https://en.wikichip.org/wiki/arm_holdings/microarchitectures/cortex-a8 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Does anyone know of any physical CPUs that adhere to some relatively simple model? E.g., a simple in-order processor, with some ability to profile execution times?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
BHive: A Benchmark Suite and Measurement Framework for Validating x86-64 Basic Block Performance Models http://groups.csail.mit.edu/commit/papers/19/ithemal-measurement.pdf …pic.twitter.com/KTSe3XDS4T
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
tl;dr: don't fine-tune, rewind.https://twitter.com/alex_renda_/status/1205902249488195584 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
Ever wondered what happens when you freeze all the weights in a neural network and only train batch normalization? Me too! Turns out you can get 80%+ accuracy on CIFAR-10 by doing so. Check out our poster and oral in the SEDL workshop in West 121. With David Schwab and
@arimorcospic.twitter.com/wdMuwMMiQu
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
How do the lottery ticket hypothesis and the loss landscape relate? Winning lottery tickets always find the same, linearly-connected optimum. Check out our (
@KDziugaite,@roydanroy,@mcarbin) poster at the SEDL workshop (West 121) and our new paper https://arxiv.org/abs/1912.05671 pic.twitter.com/uPwQKifo1W
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Come check out our poster! We present thorough experimental validation of a pruning technique based on the Lottery Ticket Hypothesis, showing how to match state-of-the-art pruning results with a simple technique. We’re at the SEDL workshop at
#NeurIPS2019.@jefrankle@mcarbinpic.twitter.com/wGNhFjKx4g
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
i'll be presenting a poster on learning a semantic parser from zero training examples at the emergent communication workshop at
#NeurIPS2019 tomorrow. come check it out! https://alanamarzoev.github.io/pdfs/unnatural_language.pdf …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Come chat about using Tiramisu for sparse neural networks and LSTMs! The afternoon poster session is 3:30-4:30, in rooms 11 and 12 at the
#NeurIPS2019 MLSys Workshop.https://twitter.com/jefrankle/status/1205549233740353537 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
Learn more about how Deep Learning can be used for performance modeling; I will be giving a talk about Ithemal (https://github.com/psg-mit/Ithemal ) at the ML for systems workshop (http://mlforsystems.org/schedule.html )
@mcarbin@samanprabhath@alex_renda_#fcrc2019#isca2019Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
RESULTS: Using a corpus of over 1M basic blocks and just their measured performance, Ithemal learns to predict performance with half the error of LLVM's and Intel's tools.pic.twitter.com/MtBvpDHAqX
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Alex Renda proslijedio/la je Tweet
How fast will your code run on the latest Intel chip? Find out with Ithemal (https://github.com/psg-mit/Ithemal ). With only black-box access to a processor, we use machine learning to answer the question (https://bit.ly/2IGDeJO ) with half the error of Intel's own tools.
#icml2019Prikaži 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.