No video :(

Latent Dirichlet Allocation (LDA) with Gibbs Sampling Explained

Подписаться 78 тыс.

Просмотров 8 тыс.

50% 1

❤️ Support the channel ❤️
/ @aladdinpersson
In this video I explain LDA and go through a tutorial paper on how it works using collapsed gibbs sampling. The next video will be a implementation video :)
This method is an old school method and it's not clear how useful it is today, but a lot of course teach this topic so it must have some historical value I feel. It's one of Andrew Ng's most cited papers!
Paper tutorial: coli-saar.github.io/cl19/mate...
Paid Courses I recommend for learning (affiliate links, no extra cost for you):
⭐ Machine Learning Specialization bit.ly/3hjTBBt
⭐ Deep Learning Specialization bit.ly/3YcUkoI
📘 MLOps Specialization bit.ly/3wibaWy
📘 GAN Specialization bit.ly/3FmnZDl
📘 NLP Specialization bit.ly/3GXoQuP
✨ Free Resources that are great:
NLP: web.stanford.edu/class/cs224n/
CV: cs231n.stanford.edu/
Deployment: fullstackdeeplearning.com/
FastAI: www.fast.ai/
💻 My Deep Learning Setup and Recording Setup:
www.amazon.com/shop/aladdinpe...
GitHub Repository:
github.com/aladdinpersson/Mac...
✅ One-Time Donations:
Paypal: bit.ly/3buoRYH
▶️ You Can Connect with me on:
Twitter - / aladdinpersson
LinkedIn - / aladdin-persson-a95384153
Github - github.com/aladdinpersson
Timestamps:
0:00 - Introduction
1:18 - What is topic modelling?
2:41 - LDA
13:30 - Posterior Inference
15:09 - Gibbs Sampling
18:06 - Collapsed Gibbs
21:50 - Finding conditional probability
26:48 - Implementation
30:08 - Pseudo code
32:25 - Ending

Опубликовано:

7 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 11

@stanislawcronberg3271 Год назад

I really like the recent uploads. Bra jobbat mannen :D Reading another comment, I think it's useful to not just jump into SOTA methods because a lot simpler things tend to be the backbones for many of the SOTA methods. I find it extremely useful when you make videos like this one, because it just helps broaden my knowledge on new topics. Looking forward to more of these! But really just keep doing what you find interesting because I'm sure I and others will be interested as well :)

@ishanmistry8479 Год назад

Thanks for the video! Just curious as to what app you were using as the pdf reader in the video.

@hissaanali5860 Год назад

Which tool are you using to show and edit pdfs ?

@ahmadulfijihaddzulqornain6790 Год назад

Oh my goodness, you have completely alleviated my stress for the past few weeks. It was extremely difficult for me to understand the generative process. I'm currently working on my final degree assignment. This video is hugely helpful! I'm wondering if I can ask you more questions through LinkedIn or another social media platform.

@AladdinPersson Год назад

I'm definitely no expert in LDA so not sure how helpful I can be, but glad it gave you a good start in the topic. I haven't uploaded the video yet, but have a video on implementation of it from scratch in Python. If your assignment is to do that then it might be helpful too: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-4DsgCZ3KTNk.html

@ahmadulfijihaddzulqornain6790 Год назад

@@AladdinPersson Thank you very much! I read somewhere that topic coherence can help determine a good model. Do you have any ideas on how that might work?