วีดีโอ

What a guy, you definitely eased my fear of agents.

thank you can we have this notebook

Are the slides available?

Are the slides available too?

one additional question - @ 1:09:00, you state shape of Q as ~600 x 20, reduced from ~9000 x 600. So 600 movies are represented by n=20 latent features. Correct me if I've misinterpreted. Given that, what does the output of a recommendation look like from Q? Are specific movies maybe clustered within those latent features? I'm a bit confused as to how the output of SVD would be plugged in a rec system. TIA!

Mitchell talks about how she thinks current tech doesn't make analogies and how she is working on something else. Questions are all asking about how aspects of current tech could somehow be analogies sort of. Except the last question. Maybe insects do analogies, too. And that is an interesting question. I can recommend Peter Godfrey Smith's Metazoa. It would be intriguing if an analogy making module was found relatively early in nervous system evolution.

please can you share slides

Simple Popularity based Recommendation, Collaborative Filtering using Matrix(2D) , Content Based Filtering. These 3 methods are mainly described in the video

In the last method of Matrix Factorization SVD was used. Can an Autoencoder be used ? Will it be computationally very expensive? Also will the quality of recommendation get any better or stay similar?

45:25 - Importance of matrix Sparsity

Advanced Agentic Literacy this video is gold one of the best videos on what works and doesn’t amazing I will teach it to my 45000 staff in our bank spot on.

awesome

You made me undesratnd the chronology of things are suppose to be in A Recommender System and m very grateful Thank You very much Jill.. Gonna go read your medium posts😉

So in summary it’s training a regression model for predicting demand and then use the model to get the demand curve and finally use an optimizer to maximize profit?

Thank you for putting this up for free

these 2 techniques are super old. Like Pre-2018 Era. Most systems like Tiktok, Instagram and etc use a two tower approach instead...

Nice webinar, any online resource/example/tutorial on how to do this technically?

👍

At 1:17:00 If your values are continuous you can keep a threshold for eg: thres = 2 5 - 4 < thres is considered close whereas 5 - 2 > thres it's not close. Now, you have a binary matrix for precision and recall

matrix sparsity of MovieLens 20M Dataset using your code is 0.54% where my findings imply the matrix sparsity is 100-0.54=99.46% which makes more sense after all. I dont understand. isnt the formula sparsity=(#zero valued elements)/(#total elements) ?

02.07.2024: Semantic Kernel : 20k stars, 1.3M downloads, 268 contributors Langchain : 88k stars, 81M downloads, 477 contributors

@ternaus I love your hair looks good on you!🎉 Congratulations on this one

Had a meeting with them last week. As of now, bb ai will be released next year but don’t quiote me on this

Thanks great overview!

Completely usless model. Models learn from the past data . They cannot predict the future. Once political event can completely turn the model parameters upside down.

not a denmo what a garbage

The mic. It's so painful to follow. Please, next time you record a conference fix this :)

Hi, thank you for your presentation. Could you please give me the source and dataset for this model?

it seems great but in practice this only works for very small subset of false predictions, which is not worth it in a critical usecase or non critical usecase

thanx.

33:30 That would actually just be a better test to see if a human is a robot.

Can we get the notebooks?

thank you so much bro

17:00 Calculating the average rating

Which white paper is referred in this video? Can i get link?

Dear Jil, Your tutorial is extremely helpful and well presented - well done! However, I do have a small question about the section where You discuss sparsity. In most documentation I see that sparsity is measured by getting the quotient of number of zero or missing values / total number of elements in the matrix. However, You're taking the number of ratings (rather than missing values) into the formula - why? Considering that we have 610x9724=5,931,640 elements and 100,836 ratings - it would seem that our sparsity should be quite big (as most data is missing)! Also, could You point to any documentation which discussed at which levels of sparsity the CF methods should be used? Best regards, Pawel.

tks for sharing

Subpar model 😂. I legit made something better...by myself with $500. I guess everything is so new, it seemd few actually understand how to build a SOTA model. Guess this was a POC though.

Bard got trained on hundreds of trillions of tokens vs 700 billion tokens for Bloom model.

Thank you for sharing your experience which we don't hear from Google and OpenAI

Okay, I nominate this guy to be future Marty McFly in "Back to the future 4"

great talk! lovin' the technical details about training

Very educational, I am only as non-technical novice, especially with Gen AI and Foundation Models. I learned from 40 minutes.

Has it been 10 weeks already?

sorry, don't think that slide on 6:49 was explained well.

I think you should have started from a checkpoint & trained on your private dataset, just monitoring test performance on MMLU and your finance metrics.

This man is a genius

look into

FinGPT is better tho.

방송도 버출얼 캐릭터들이 많이해. 물론 사람이 하는건데, 이것도 AI화 될수있어. 그럼 그것도 인간이 할수 없을꺼야.