Daniela Rus presently serves because the Director of the Pc Science and Synthetic Intelligence Laboratory (CSAIL) at MIT. Rus is …
source
Tags: aiartificial intelligenceartificial intelligence newsartificial intelligence news 2023BusinessEntrepreneurshipfinanceForbesForbes DigitalForbes MagazineForbes MediaIdeaInvestinglatest news about robotics technologylatest robotslatest robots 2023Learnliquidmachine learningnetworksNeuralPersonal Financerobot newsrobotics newsrobotics news 2023robotics technologies llcrobotics technologytechnologyTraining
Relevance realization
Has Elon seen this?
that's the most impressive thing i have ever seen,kudos to the researcher
good for alignment if the arch works well
But, just because that first car is focused on e.g. the side of the road (which is perhaps a heuristic visualization anyway), that's not bad. What if, for example, there's a kid on the side of the road, I'd want the network to be on the lookout for that!
Hey, Any link to the paper or git repository?
Sky Net
They always start off with AIs potential in healthcare. After trying to work with AI that’s made for radiology and ophtho, I can tell you that it’s currently incompetent. Nowhere near what chatgpt can do.
This is cool and all but I recommend watching the original talk by Ramin Hasani. The salience map she shows for the traditional neuron is being made intentionally bad by introducing noise into the input image, whereas the liquid neuron example is not affected by the noise. Slightly dishonest representation of the results
Umm we are witnessing the next best thing in AI doing real things, wait til this becomes main stream. Props to this team.
❤❤❤
very cool. I look forward to the many applications this can be used in. Thanks for sharing.
Ok if this is true is one big advance like CNN were in their time.
It's a little bit of cheating to give one NN a noisy camera input stream and the other a clear stream, isn't it? 😉 Either way, I'm looking forward to some implementations of this.
Just remember MIT was already working on this last year maybe longer. Don't let them have your biometrics. They will own you and everything you think you own. It will be as easy as hitting delete on a keyboard to totally erase you.
I for one welcome our AI overloads
This seems like a bigger breakthrough than whatever else on the AI news in the past couple of months?
Isn't that another huge step in the direction of AGI?
👍
I hate to burst your bubble, but this isn’t a new idea. It’s just the first time someone in academia wrote about it.
I was wondering a few days ago about black boxes and now we have liquid neural networks. Amazing 😍
This is huge.
Robust under data distribution variance. By targeting more task relevant features. This means less data necessary for continuous learning which is the only and super costly way to keep a model in production.
Please make something like skynet
WOW! Amazing, thanks for sharing Forbes! 🚀
Мне пару млн долларов нужно было а не эти гниды
1:12
yeah well basically they mimic focusing like we do and are robust to context change … at last !