christian scheier

@TheXeophon Want

Super excited to share what I've been working on 👀 You know the struggle: You want to use a project, but it has a GPL or CC-by-NC license 😭 We worked hard and our AI-based agents convert any repo to an MIT-licensed one 🚀🚀🚀 Comment "Want" to get early access 👇🏼

@jeremyphoward @curtwehrley may be interesting in this context - have just bought this for myself and it works well for me at work walkolution.com PS: thank you for your awesome fastai lib!

@curtwehrley Wow thanks!

Has anyone else noticed that walking whilst learning gives better results? Are there any studies of this phenomenon? sethroberts.net/2012/09/09/ind…

@timo_schick @OpenAI this is extremely helpful, thank you very much!

📝I wrote a blog post that explains few-shot learning with Pattern-Exploiting Training (and how it can be used to outperform @OpenAI's GPT-3 on SuperGLUE) in simple terms: timoschick.com/explanatory%20… Would be happy to hear your feedback😊#NLProc

@pmbaumgartner Very interesting! Is there a way to access this material without an account?

@fchollet Die üüä33ä übüüer4üää4ääüü6t unäöd5üää5ä ääältesäte4zuäüv5ää5 Bär an u9ä9ilääüäär ö für 54 Jahren und undüää5ä 4 Jahren in Jahre

I think the notion that there's a "deep learning framework war raging" is pretty mistaken. It's not like there are different clans that don't talk to each other. The majority of people use multiple tools, often within the same project.

@bradenjhancock Image classification would be very helpful , thank you

Twitter poll: We're making a bunch of tutorials for the next major release of #Snorkel later this summer. What tutorials would you like to see? These can be focused on a task (e.g., image classification, relation extraction), technology (e.g., plugging into Spark, TFX) or other.

Grand Mufti Amin al-Husseini, respected Muslim cleric living in Baghdad, has declared a jihad to drive "British infidels" from Iraq & Palestine.

@quasimondo Yes, tested within Yes tested with feature contrast images (like the popout stim you show) as well as plenty of real world images vs ground truth. Was impressed.

@chris_scheier Did you try that particular pattern on SalGAN? I am be curious if it gets it right.

This gaze estimation model still has a lot to learn.

@quasimondo Are u trying SalGAN? Worked for me

I believe that this architecture will never be able to solve this intelligently since it would require it to recognize that there is a pattern and something is off. It can probably learn this particular configuration, but not generalize.