Jayani Withanawasam.

Grad student at The University of Tokyo. Curious about how we as humans make sense of what we see!

[Michal Fabinger @fabinger]

I'm happy to announce major changes to Tokyo Data Science @TokyoDS:

(1) Fair Play Tuition makes it affordable to *anyone* https://t.co/qSho2lO8ZX

(2) You can join even for a course or two

(3) Name changed to Acalonia @acalonia_x since it's global

Pls retweet for visibility🙏

[Jayani Withanawasam. @jaywith_7]

"I'm human, you know?" This one is epic! 😅 Another fun episode in #humansofai

[Devi Parikh @deviparikh]

Yejin Choi (@YejinChoinka) on Humans of AI: Stories, Not Stats!

Video: https://t.co/o4FG0UB279
Podcast: https://t.co/ngAdYagI1U
All episodes so far: https://t.co/p6oy1RmN7I

[CSE @ UOM @cse_uom]

Introduction to Data Science - Session 13
September 30, 4:00PM

"Deep learning for medical imaging" by @kau_mad

[Jayani Withanawasam. @jaywith_7]

The much-awaited episode is out! It was so much fun and so many things that I can relate to.

[Devi Parikh @deviparikh]

Me on Humans of AI: Stories, Not Stats :)

Video: https://t.co/kYhy0Oqxv9

[Kaushalya @kau_mad]

Thanks to the JAX/Flax community week, I had a chance to fine-tune a CLIP model on a radiology dataset (ROCO) on cloud TPU-v3-8. It was a quite fun learning experience.
☞Github repo: https://t.co/fms0foBdRE
☞@streamlit demo on @huggingface 🤗 Spaces: https://t.co/nlk7AuQmBo

[MIT CSAIL @MIT_CSAIL]

"The first step of any project is to grossly underestimate its complexity and difficulty."

- Nicoll Hunt @nicollhunt

[François Chollet @fchollet]

When we get a new idea, our impulse is to look for signs that could validate it. But the most effective way to make real progress is to look for the simplest way to prove your idea wrong.

[Kaushalya @kau_mad]

Clean Pytorch implementations of ML techniques with explanations next to the code. This is a format that makes understanding papers way easier. @__MLT__

[Jayani Withanawasam. @jaywith_7]

My favorite! 🤣

[Jayani Withanawasam. @jaywith_7]

@LittleLeapers_ finally found the purpose of these stickers!!!

[Dr. Bella, tired and wired @LittleLeapers_]

Woke up to a rejection letter which sucked. But at least I got to add a sticker to the page.

[Christian Wolf (🦋🦋🦋) @chriswolfvision]

I passed this image through a pretrained ResNet 101 with @pytorch and it predicts:

Tiger shark 23%
Hammerhead 21%
Great white shark 16%
Gar, garfish 11%
Sturgeon 3%

My conclusion : shape > [ texture + mountain context]
=> reassuring in some way.

(Image from @SolTight)

[Jayani Withanawasam. @jaywith_7]

Sacred is quite useful for quick experimental results analysis (even without integrating Omniboard while using FileStorageObserver). And it took ~< one hour to learn and setup as well. 😇

[Daniel Daza @danieldazac]

While Tensorboard is a great tool backed by the community behind @TensorFlow, lately I've been using an alternative to log my experiments that consists of two tools: Sacred and Omniboard. In this thread I'll share what I love about them and maybe convince you to try it out!

[Jayani Withanawasam. @jaywith_7]

great questions indeed! you two are goals 😍

[Devi Parikh @deviparikh]

Episode 1 is out! Dhruv Batra (@DhruvBatraDB) on Humans of AI: Stories, Not Stats.

Video: https://t.co/JRjwHUczPp
Podcast: https://t.co/a6jlTTdswM

All episodes so far: https://t.co/dXeuh0PBOD

[Karan Goel @krandiash]

We're bringing you the 2nd episode of the Stanford MLSys Seminar tomorrow. @matei_zaharia will talk about lessons from @databricks in building and deploying @MLflow.

Tune in at 3pm PT Th at https://t.co/SxSoEeBTW1 (and join our mailing list at https://t.co/vyFNMaH1pc)!

[Workera @workera_]

Looking to better understand the AI project development life cycle? Download our report to learn about the differences between ML and DS project development cycles: https://t.co/CLYnl9yAg4

#ArtificialIntelligence #MachineLearning #DataScience

[François Chollet @fchollet]

I don't mind electronic gadgets, but I draw the line at connected ones. Those tend to have more power over you than you have over them

[Jayani Withanawasam. @jaywith_7]

@MAKSBoralessa @fabinger That's exactly what came to my mind also. Had to live more than 20 years under civil war in SL. :(

[Jayani Withanawasam. @jaywith_7]

This was exactly my confusion back then 🙄. How can someone memorize all those sophisticated words?!

[Animesh Garg @animesh_garg]

Many schools have dropped (or made optional) the GRE requirement -- a step in the right direction.
btw GRE is optional at @UofTCompSci as well!

It is an undue burden for non-native speakers to memorize words far too recondite for prosaic usage!