[13] Adji Bousso Dieng - Deep Probabilistic Graphical Modeling
The Thesis Review
The Importance of Topic Models in Deep Learning
The ETM is a very impactful work, but that's not seen in the deep learning community because they don't really care about topic models. The focus is not on those things. We wanted to package your ETM, ETM work into R. That's the family of models they use. And leveraging now deep learning within probabilistic topic models, we managed with the ETM to solve all the problems. You can scale to very large vocabularies. Inference is fast and efficient. So you have all those, this is the data that they were, that's relevant to those communities.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
