Jin Yi @yongjinyi12

Jin Selangor, Malaysia Joined March 2014

Tweets

300
Followers

28
Following

126
Likes

680

Jim Fan @DrJimFan

3 years ago

The Adam optimizer is at the heart of modern AI. Researchers have been trying to dethrone Adam for years. How about we ask a machine to do a better job? @GoogleAI uses evolution to discover a simpler & efficient algorithm with remarkable features. It’s just 8 lines of code: 🧵

39 558 4K 835K 2K

Download Image

elvis @omarsar0

3 years ago

Open Problems in Applied Deep Learning If you're looking for interesting open problems in DL, this is a good reference. Not sure if intentional but it also looks useful to get a general picture of current trends in deep learning with ~300 references. arxiv.org/abs/2301.11316

21 231 971 108K 464

Download Image

Jonas Andrulis @JonasAndrulis

3 years ago

ChatGPT is basically useless for high-value work. An expert (e.g. lawyer) needs explainability, sources and a way to influence and control outcomes. I am proud of what our team achieved with AtMan. Making multimodal generative AI trustworthy. arxiv.org/abs/2301.08110

36 214 1K 235K 663

Download Image

Perplexity @perplexity_ai

3 years ago

Announcing Perplexity Ask, a new search interface that uses OpenAI GPT 3.5 and Microsoft Bing to directly answer any question you ask. perplexity.ai discord.com/invite/kWJZsxP…

65 430 2K 0 824

Download Video

Shreya Shankar @sh_reya

3 years ago

It's been ~15 months since I switched fields (into DB) and started a PhD, so I did a bit of freewriting. I reflect on ML engineering and some uncomfortable learnings: shreya-shankar.com/phd-year-one/

22 77 743 0 338

MMitchell @mmitchell_ai

3 years ago

Last week, a major AI milestone was hit: the BLOOM model was released, for everyone (including you!) to examine. What is this, and why is this important? 🧵👇 huggingface.co/bigscience/blo…

11 226 863 0 336

Erik Bernhardsson @bernhardsson

4 years ago

I wrote a blog post about how to build at data team in the form of a story (and it ended up being about 4x longer than I anticipated): erikbern.com/2021/07/07/the…

26 144 736 0 226

Tom Goldstein @tomgoldsteincs

4 years ago

My lab is building neural nets that emulate human “thinking” processes. They increase their intelligence after training by increasing their compute budget. By doing so, a net trained only on “easy” chess puzzles can solve “hard” chess puzzles without having ever seen one…

13 189 1K 0 272

Download Image

David Pfau @pfau

5 years ago

If you follow me on Twitter, you probably know that I am pretty allergic to hype, especially around deep learning. So believe me when I say - this is a big f---ing deal. deepmind.com/blog/article/a…

13 175 1K 0 88

hardmaru @hardmaru

5 years ago

How do you skim a research paper? I usually read (in order): 1) abstract 2) 1st paragraph of the intro 3) last paragraph of intro (for contributions) 4) 1st paragraph of the conclusion (it's usually one paragraph anyways) 5) figures / tables of results, and read their captions.

44 319 2K 0 360

AI at Meta @AIatMeta

5 years ago

Today we’re announcing milestones that push the limits of #embodiedAI: the first-ever audio-visual platform; a new framework for building top-down semantic maps & episodic memories; and SoTA in navigation & exploration of unfamiliar spaces. ai.facebook.com/blog/new-miles…