Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @lilianweng
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @lilianweng
-
Prikvačeni tweet
Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised learning manner. My latest post covers many interesting ideas of self-supervised learning tasks on images, videos & control problems:https://lilianweng.github.io/lil-log/2019/11/10/self-supervised-learning.html …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I just realized that I missed another category of curriculum learning methods, so I added it in. Now the overview figure looks like this:pic.twitter.com/xofFlKMZfO
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lilian Weng proslijedio/la je Tweet
An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.” http://joschu.net/blog/opinionated-guide-ml-research.html …pic.twitter.com/fyO6cyr9im
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Humans learn from curriculum since birth. We can learn complicated math problems because we have accumulated enough prior knowledge. This could be true for training a ML/RL model as well. Let see how curriculum can help an RL agent learn:https://lilianweng.github.io/lil-log/2020/01/29/curriculum-for-reinforcement-learning.html …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Thank you all! Now I have quite a list of topics to consider, which is likely enough to cover the entire 2020.
#Hello2020Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I couldn’t decide the topic of my next post. Would like to hear your ideas. Plz reply! Thanks <3
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lilian Weng proslijedio/la je Tweet
Over the past 5 months we’ve been experimenting how to steer a mammoth without training it. Here is how.https://eng.uber.com/pplm/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lilian Weng proslijedio/la je Tweet
And yet, it feels like we're just getting started. If you're interested in this line of work, we're hiring for robotics team! I'm quite excited about what we'll be working on in 2020. https://openai.com/jobs/ https://twitter.com/gdb/status/1184183075606974464 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It has been a long journey for us. There were moments when I felt disappointed or almost hopeless, but the progress we have made, together as a team, is credible. We made it through and made it happen. Check it out!!https://twitter.com/OpenAI/status/1184135128869527552 …
0:18Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lilian Weng proslijedio/la je Tweet
Loved your talks last night! Thank you for hosting us
@OpenAI@AmandaAskell@nadipity@mcleavey@miramurati@lilianweng Photos: https://buff.ly/2Q7cwRL




#robotics#AI#womenintech#girlgeekxopenaipic.twitter.com/IAdjBo1XsI
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I might be too late into the party, but this Japanese show is so cool: Your turn to kill / あなたの番です —- while watching, you need to take notes, think hard and solve math problem (i.e. hat matching problem). Fun, right?
#YourTurnTokill#nospoilerspic.twitter.com/glmgbyGGnE
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Would like to thank
@hardmaru! I got the idea of writing this when reading http://blog.otoro.net/2017/10/29/visual-evolution-strategies/ … :)Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Gradient descent is not the only option when optimizing model parameters. Evolution strategies can help too. Check out my new post if you are interested in how CMA-ES works or the way ES is used in deep RL:https://lilianweng.github.io/lil-log/2019/09/05/evolution-strategies.html …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lilian Weng proslijedio/la je Tweet
12 years ago I tried making my first poker AI in college and dreamed of beating the world's best pros. After seven years of a PhD, I'm excited to announce that I finally did it! It's been quite an adventure. Looking forward to the next one!https://twitter.com/facebookai/status/1149378129464569858 …
0:36Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Einstein Field Equations - for beginners! https://youtu.be/foRPKAKZWx8 —- such a brilliant video, cannot stop watching.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is really cool. You should give it a try if you are training vision models on simulated images
https://twitter.com/OpenAI/status/1144622103942979585 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Meta RL is a great idea
: After trained over a distribution of tasks, an agent is able to solve a new task by developing a new RL algorithm with its internal dynamics. Check my latest blog post if interested:https://lilianweng.github.io/lil-log/2019/06/23/meta-reinforcement-learning.html …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Also this one, approximating CNN as a bag of local features works well on ImageNet:https://openreview.net/forum?id=SkfMWhAqYQ …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Two most interesting papers I’ve found recently: “the lottery ticket hypothesis” https://openreview.net/forum?id=rJl-b3RcF7 … (probably already very famous) and “adversarial examples are not bugs but features” https://arxiv.org/abs/1905.02175
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.