Lasting collaborations can come from transient places.

One of my collaborations came out of a train ride 🚊 where I traded notes with a mathematician, en route to Stockholm. Followed by making these corgis happen.

Story πŸ§΅πŸ‘‡πŸΏ Image
On the 4 hr 🚊ride, I talked about generative models and neural networks. He talked about fractals and Mobius transformations β€” and even how all this ties into making better compression socks 🧦.

Hours 1-2: Just a pen and a few loose pages.
Mobius transformations generalize affine transformations
(see cute dogs). They are found naturally in biology. Maybe... we could use these for data augmentation, without much tuning across a ton of different augmentations.

Hour 3-4: Hacking on a Python Notebook together. Image
After I leave Sweden, we jump on calls together every now and then with progress updates. I find others interested too.

Next several months: Throw some experiments setups at it and see if our intuition validates our hypothesis.
The team works hard, results have promise. Several rejections in the middle.

Then, a few weeks ago: Published πŸ“œ with Jiequan Zhang, @hjian42, Torbjorn Lundh, @AndrewYNg.

Demo and code github.com/stanfordmlgrou…
Paper arxiv.org/abs/2002.02917
iopscience.iop.org/article/10.108…

β€’ β€’ β€’

Missing some Tweet in this thread? You can try to force a refresh
γ€€

Keep Current with Sharon Zhou

Sharon Zhou Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @realSharonZhou

15 Jan
Excited to share our #ICLR2021 paper w/ CS & math depts @Stanford 🎊

Evaluating the Disentanglement of Deep Generative Models through Manifold Topology!

w/ @ericzelikman Fred Lu @AndrewYNg Gunnar Carlsson @StefanoErmon. Acknowledging @torbjornlundh Samuel Bengmark.

Thread 🧡 Image
Before I start: camera-ready πŸ“Έ & math-inclined R5 burn πŸ”₯ are here
openreview.net/forum?id=djwS0…

Huge appreciation for all reviewers esp R5 in making our work better.

My goal in 🧡: Explain our work in my simplest terms to you. Don't worry if you get lost, it's admittedly dense :)
Disentanglement in your generative model means dimensions in its latent space can change a corresponding feature in its data space, e.g. adapting just 1️⃣ dim can make the output "sunnier" β˜οΈβ†’πŸŒ₯β†’β›…οΈβ†’πŸŒ€β†’β˜€οΈ Contrast w/ this entangled mess β˜οΈβ†’πŸŒ₯β†’πŸŒ©β†’πŸŒͺβ†’β˜€οΈ
Read 16 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!