Hope this will pave the road to Symbolic AGI/Symbolic ASI where are AI is fully explainable provable.

Thank you for the presentation that clearly spells out NLP tasks in RL!

First author talks about his paper!

Where we get a course in Symbolic AI , please tell , University's courses

Love this talk Jeff! Awesome summary

4 years ahead of his time.

The issue of scalabality plagues Tree-LSTM structures

That tool is exceptional! Please, I would like to test it! When will it be available to the public?

So elegantly presented. Kudos to Colin and team!

Awesome content !Where do I get these ppts used in lecture delivery?

9:41 thru 16:14 Very informative for learning CCG Supertagging

10:37 , is that garden path sentence intentional?

nice talk but you should slow down a bit. too fast

how can we try it ?

NO mention of "overfitting" anywhere in the past few years of these huge models and datasets. The fundamentals of ML are out the window

You cover so many different good ideas here! What a ride!

It doesnt load :( Can you fix it or did you take it offline?

Still relevant as ever in 2022

What is the gradient for the frobenius based error function relative to W and b? It's not in the paper and I couldn't find it in the references given

Clear and coherent explanations

clear explanation !

Best video on rules extraction. Thanks .

Do we always have to choose the number of samples to draw in the beginning or can we draw more later?

Awesome ! Thanks for sharing

Where can I can the slides from?

btw, I really appreciated the "functional" view of CCA. That was especially helpful to me.

I find the comment of the data views a little confusing. I have never seen that point to view. Perhaps that's why it's confusing to me. The way I understand that after further reading is that in reality general functional CCA finds two functions that correlate a collection of random variables x1, x2 (where the coordinates are random variables). The random variables might have a correlation or not. But I guess in Galen Andrews's work he is has applied it to data that comes form the same source - why I think he refers them as views. Essentially, that assumption makes it clear that the r.v.s should be correlated since the data is the same - i.e. the generation of data is from the same source but it generates different views i.e. different r.v.s. So the assumption (from the example) is that there *must* be some correlation, due to the problem setting. Which is fine, just trying to understand the general framework, application, etc. Good video in general! Thanks for sharing.

To this wonderful professor of Pennsylvania University

Rip ....

whereis the codes for implementation ??? thank u

Could you post a link to the slides? They're a bit blurry in the video

Even our innate machinery came about through an evolutionary process. Is that not a form of "learning". I doubt what he is talking about could be explicitly designed, so in the context of AI Yann would be the one who is correct. You'd have to learn the innate structure, not design it by hand.

Thank you so very much for this. Deeply Indebted.

I like your presentation very much. Thanks

Wow, I've read some papers of Jack, surprised to see a presentation of him!

Nice video!

Do you have the code in a Github repo anywhere?

Awesome work! Any newer research you folks did on this topic?

What a cool talk

The idea of not relying on logical forms is really cool! This is an impressive project!

It's becoming clearer that with all the brain and consciousness theories out there, the proof will be in the pudding. By this I mean, can any particular theory be used to create a human adult level conscious machine. My bet is on the late Gerald Edelman's Extended Theory of Neuronal Group Selection. The lead group in robotics based on this theory is the Neurorobotics Lab at UC at Irvine. Dr. Edelman distinguished between primary consciousness, which came first in evolution, and that humans share with other conscious animals, and higher order consciousness, which came to only humans with the acquisition of language. A machine with primary consciousness will probably have to come first.

Very interesting

Colin breaks the mold of a typical researcher by also being extremely eloquent. Save some talent for the rest of us Colin!

Excellent approach to understand text

Liked even before I started watching.

Amazing talk!

Love her approach to any feedback with a more or less truthful reply! But she's getting grilled, no doubt 😂😂. Good luck ma'am! AI2 we're all a BIG fan of you! Thank you for the community service you've done!

THANK YOU IN EVERY POSSIBLE WAY!

27:00