I have been waiting for an update on this company for about a year. Thanks for having them on!
@ashh30515 ай бұрын
I think Jason got a bit confused at 13:20 and the interviewer didn’t do a good job of catching this. I’m guessing that Jason was thinking that current neural networks are like “human brains” and the liquid neural network was based on a worm brain. This is a mistake as current neural networks are not like human brains. I think the liquid guy would claim that his architecture is closer to the human brain than traditional NNs as his design is more based on biology.
@SteveMayzak4 ай бұрын
Hilarious that our current neural networks are named as such. I guess that name was take so Liquid it is! Seriously cool
@timeTegus2 ай бұрын
@@SteveMayzak most neural networks are more like human brains. but trasformers are a bit of a exeption. they seem more distant. but they also seem to scale very good.
@SB3245 ай бұрын
Catch that Joscha Bach name drop at the end! If Joscha is on the team, they’re on an entirely different level
@circlelabs5 ай бұрын
Wow, insane tech
@DonaldHarvey-yi2tg5 ай бұрын
0:22
@MichaelCoker-st3cd5 ай бұрын
Why didn't the liquid AI driving test also contain the same amount of noise as the standard test? It seems slightly unfair and the liquid AI attention map seemed to just have attention *everywhere*. I'd love to see a test where they throw a ball out in front of the vehicle as well. I'm still super interested in this tech to see how it works and the potential for lower power/processing needs.
@KCM25NJL2 ай бұрын
If you watch the actual staged demonstration video, they do go on to add noise to the LNN demo and it does prove to be largely unaffected.
@JetLagRecords5 ай бұрын
This Week in Startups, Your videos always make me happy, so I subscribed!
@gridvid5 ай бұрын
Awesome. Liquid Networks are awesome. Keep it up
@Renaudpc5 ай бұрын
I love this approach. Why try to create the human brain when you can create an earliest version of it, learn the ins and out and evolve.
@Renaudpc5 ай бұрын
I love this.
@SB3245 ай бұрын
Glad you had Ramin on!
@Mheme-f7n5 ай бұрын
Ramin Hasani!!!!!!!!!!!!
@droh_it5 ай бұрын
Technical question for the founder. Can you do multivariate time series anomaly detection with liquid neural networks?
@roycedsouza29635 ай бұрын
Why don’t you just use tabular analysis?
@hamandchees35 ай бұрын
Wish jcal asked more about how liquid neural networks work in practice-- how are they pretrained, how sample efficient are they, do they have published scaling laws, etc.-- rather than diverge off into hot topics.
@petratilling25215 ай бұрын
They should go for the high-end personal market as well. I want a whole-house self contained model that comes with the ability to plug in verticals and learns as we go. I really hope they blow past ALL current architectures.
@nicktrish20085 ай бұрын
Please give Elon this guy’s number?
@danielscott20625 ай бұрын
No. I've seen his code. Spent too much time fixing it... His Liquid CNC paper was interesting but ultimately couldn't be reproduced. The best minds create and publish clean code. Sorry Ramin.
@ps33014 ай бұрын
Since Elon is a first principle analysis kind of guy, if he is presented the liquid neural network which is much better in self drive and consumes a lot less power, Elon will be adopting it if it consumes 10 times less power. Self drive chip consumes a lot of energy.
@talentsherpa5 ай бұрын
This week in startups us my compass. Thanks
@游淯聖-j5p4 ай бұрын
Can someone explain to me what this "liquid" stuff is? I dont see the special of this, just a varient of ODE and even worst experiment result, in the end is this just another RNN like model?
@petratilling25215 ай бұрын
This is the way.
@petratilling25215 ай бұрын
This idea that only “bad” jobs will disappear is silly. The “best” jobs will probably be the first to go.
@PeterNooteboom5 ай бұрын
This almost feel to good to be true. But I suppose time will tell.
@abdulshabazz85974 ай бұрын
This technology is promising. The reason transformer models have so many parameters is for controlled tunability which can always be controlled due to the limited way hyper parameters are employed in transformer models.. What is not advised are proposed advanced architectures with builtin runaway geometric cross-learning capabilities which this model is not.
@zacharydaniels31865 ай бұрын
It strikes me that this will be the sort of "brain stem" of AI that interacts with the real world while the "right brain" creativity will be transformers. My question is: where does the logical "left brain" architecture lie? Mamba?
@innomind5 ай бұрын
Is he Persian?
@chrisredlich90862 ай бұрын
Even if AI comes up with the most elegant solutions for energy or other issues, it’s impossible to say how that will be used. If it is politically inconvenient, I guess it will be shut down under the table.
@hobocraft05 ай бұрын
Finally, some good old fashioned bio mimicry. Who is the reference? God.
@zacharydaniels31865 ай бұрын
Excellent point.
@juliusapriadi4 ай бұрын
...and as usual, no word about AI Safety. Let's continue the race to AGI with better and better architecture, and then act surprised if we accidentally get killed, since no one bothered waiting for alignment to be solved.
@rw92072 ай бұрын
It was almost funny watching Jason misunderstand and fail to grasp, almost everything Ramin said. His thinking is so rigid, it was like watching a Grandpa trying to play portal 2.