Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @risi1979
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @risi1979
-
Sebastian Risi proslijedio/la je Tweet
Here's our team, in case you were wondering. We're all standing up straight, or at least perpendicular to some high-dimensional hyperplane that is not depicted because of the inherent limitations of projecting onto a 2D plane.pic.twitter.com/K6drseaiJr
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
We have also hired a team of top-notch talent, including
@GabbBarros@_twoFactor@nojustesen@DavidMelhart@SamPSnodgrass@CIGbalance. We are incredibly grateful that these researchers, who have all done remarkable research in their own right, believe in our vision.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
We're thrilled to announce we've closed http://modl.ai 's seed round, raising $1.7M from a fantastic group of investors supporting our mission to bring the best possible AI-driven tools to game developers around the world: https://modl.ai/news/modl.ai-leading-new-wave-in-AI …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Very happy our startup
@modl_ai was able to close this seed round! Looking forward to the cool things this allows us to build!

https://twitter.com/creativedlab/status/1224701681650294784 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hopefully this will motivate more people to do research in artificial life
, instead of following the same old gradients
. On the other hand, it's also nice working in a field that's not as crowded yet
https://twitter.com/Kriegmerica/status/1216859655374299136 …
0:12Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
for example, the last issue had tweets from
@math_rachel discussing accountability,@ilyasut on deep learning theory,@risi1979 on a tool for understanding bias,@hardmaru on using ML with doodles instead of photos, @FidlerSan on a search engine for training data, and more!Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
You know that open offices are working well when a yellow coffin seems like a pleasant alternativehttps://twitter.com/mjg59/status/1218112589978193920 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
What conference organizers say "We are extending the paper deadline because of numerous requests ..." What it actually means "We do not have enough submissions and desperately need more..."
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
I love it when scientists embrace both research & education, & try to make their work understandable to general public.https://twitter.com/risi1979/status/1216775386601861121 …
0:03Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The tool combines counterfactual examples and clustering of the networks' activation patterns to empower non-experts to detect bias. For most of us, this is the first foray into fair AI methods, so any pointers to other relevant work or suggestions are greatly appreciated.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Traditionally, non-experts have little control in uncovering potential social bias in the algorithms that may impact their lives. We present a preliminary design for an interactive visualization tool, to reveal biases in neural networks.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Happy our new paper "Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples" w/
@chelmyers,@efreed52,@larispardo,@anushayfurqan, and@jichenz is now on arXiv: https://arxiv.org/abs/2001.02271@ITUkbh@DrexelUnivpic.twitter.com/KhKHhTx13NPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Is it worth arguing about what deep learning is? Hasn't DL now become more of a buzzword than anything else? Maybe time for more precise definitions and fewer umbrella terms that encapsulate a myriad of different methods?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Make sure to not work for a university like
@MurdochUni that tries to silence their employees by suing them:https://www.theaustralian.com.au/commentary/murdoch-uni-acts-on-outspoken-professor-gerd-schroderturk-to-silence-them-all/news-story/80e3436d682f2533d6048d5a7ef8baab …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Sebastian Risi proslijedio/la je Tweet
This year, the summer school is organized under the aegis of
@modl_ai, our game AI research startup, and we have speakers from@CAGames@unity3d@DeepMindAI@King_Games sharing their expertise, with more leading companies to be announced.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
it's interesting to see what kind of representations emerge that the model is not directly optimized for. In this case, the network learned to predict events important for the survival of the agent (such as not being hit by a fireball). Code will follow soon.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Interestingly, the evolved forward model seems to have learned to predict if a fireball would hit the agent at the current position. Similarly to the great work by
@bucketofkets,@Luke_Metz,@hardmaru on observational dropout (https://arxiv.org/abs/1910.13038 ),pic.twitter.com/WYlYDNid29
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
As can be seen in the t-SNE plots in the video, the compressed information that is fed into the controller of the world model contains enough information to clearly separate environmental states in which the agent should move left or right.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This idea is very much inspired by Nick Cheney,
@DoctorJosh,@sunspiral,@hodlipson great work on co-evolving morphologies and controllers for virtual creatures https://royalsocietypublishing.org/doi/full/10.1098/rsif.2017.0937 …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The age objective counts how many generations passed since a mutation. Through a multiobjective EA, we optimize for both low age and high task reward.
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.