Deep Learning: Classics and Trends (DL:C&T) is the hottest thing in town…JK. It is a reading group / talk series I have been running since June 2018. It started within Uber AI Labs, when we felt the need of a space to sample the overwhelmingly large amount of papers, and to hold free-form, judgemental (JK) discussions.
- Time: every Friday, 12pm - 1pm
- Place: Uber HQ, San Francisco
- Format: someone presents; others listen; all eat.
- Scope: deep learning, old (a.k.a. “let’s revisit the 2014 GAN paper”) and new (a.k.a. “look at this blog post from yesterday”).
- Join the mailing list to receive weekly notifications of the upcoming talk.
If you are in San Francisco, definitely consider joining in person, either as a presenter or just an observer! Drop me an email to discuss.
|Date||Presenter||Topic or Paper|
|2020.02.14||Xinchen Yan||Conditional generative modeling and adversarial learning|
|2020.02.21||Nikhil Dev Deshmudre||Contrastive predictive coding|
Congratulations! Now that you have scrolled all the way down here, you get the reward of reading more texts about the scope and vision of this reading group.
Q: What was the initial idea of organizing a reading group like this?
A: It started with the rather selfish idea that I want to know about papers that I don’t have time to read, and learn about topics my individual intelligence limits me from fully understanding. Besides, I enjoy being around people that are smarter and more knowledgable than me, faster than me working out twelve math equations on one slide, braver than me to ask stupid questions, and more patient than me answering them, as well as those who value great presentations as much as I do.
Q: How much work is it for you?
A: I never travel on Fridays now.
Q: Where do you see it going?
A: I envision a community where people work hard to tell science stories well. Each paper is a story. A great paper, apart from solid results and technical and scientific advances, stands out particularly in the way it tells the story. I hope we all value storytelling and talk-giving slightly more than we do now. This ties to an eventual wish that scientific writing moves towards being lucid and understandable. This reading group is a start.
Here is how I see different levels of storytelling, in the format of one-hour presentation, happening in this group.
You can give a Level 0 talk, which is going through someone else’s paper—the storyline is already there. This is perhaps the most basic and involves the least work: you just need to understand it and retell it to others. (I assume as a researcher you already read papers, and this additional work of making it into a presentation would definitely help you understand it better yourself.) And best of all, when the audience asks hard questions, you can just say “Not my work—I don’t know.”
A Level 1 talk, could mean presenting one of your own papers. The bar is higher because you are expected to know every detail of the project, but also lower because you probably already do. And a good background coverage to lead to the exact problem and idea always helps.
Then we have Level 2 talks, which are usually a topic formed by understanding a field (however small it is) thoroughly well, and having in mind a hierarchical chart or spiderweb of a number of fields leading to that particular one. You might be citing multiple papers, drawing connections and coming up with conclusions that are mainly your own.
Q: Do you have a high bar for talks given there?
A: Yes I do. But I also know we all have to start somewhere. And I myself was a horrible presenter not too long ago (likely still am). But we all get better.