Deepta Rajan

Dance n' Data for Science. Currently - ML for Manufacturing @Blueorigin. Always ready to workout.

[Deepta Rajan @deepdanscience]

Thrilled to share that our work won the #BestPaperAward at the #SPIEMedicalImaging conference! 🥳 @SPIEtweets 👉https://t.co/VuTzqvU9X7

Congratulations! to the awesome sauce team led by @jjayaram7 🙌👏 alex karagyris,@follow_kashyap 1/3

#CollabFTW @IBMResearch @Livermore_Comp

[Jay Thiagarajan @jjayaram7]

If you are designing Outlier Exposure-free OOD detectors, talk to us at the PODS@ICML workshop. Hint: virtual inlier synthesis + negative data augmentation is the key! @VivekSivaraman1 @RUSH1L @deepdanscience #YamenMubarka @asusensip
Preprint: https://t.co/bQflvwLGCj
4/9

[Deepta Rajan @deepdanscience]

@rakshith_subra @VivekSivaraman1 @jjayaram7 super cool poster! ;)

[Jay Thiagarajan @jjayaram7]

I will be at #ICML2022 next week! Excited to attend an in-person conference after a long time. Here is a quick roundup of our conference and workshop papers.. If you want to chat about any of our projects, or just meet for coffee, let me know :)
1/9

[Deepta Rajan @deepdanscience]

@sam94katoch @kowshik0808 @OdrikaIqbal @VivekSivaraman1 @MS_Sunil_Rao Congratulations Sam!🥳looking forward to seeing all the cool things you'll continue to do. Cheers!

[Deepta Rajan @deepdanscience]

@kowshik0808 @pturaga1 @jjayaram7 @Yezhou_Yang woah! big day...Congratulations!! 🥳

[Gergely Neu @neu_rips]

i've been submitting my work to conferences for more than 10 years, fighting to make each deadline. i have tried many strategies to cope with the anxiety and make sure that i don't have to work insane amounts of hours on the days before the deadline.
here's what i learned: 👇🧵

[Jay Thiagarajan @jjayaram7]

Hot off the press @SciReports: A short thread on TraCE, a new method for post-hoc analysis of chest X-ray models. This can be used to validate model behavior and characterize its weaknesses. Joint work with @kowshik0808 @deepdanscience @pturaga1. Link: https://t.co/ckuT7tSlz5

[Deepta Rajan @deepdanscience]

ah! the citation problem... 🙄 sigh.

[Jay Thiagarajan @jjayaram7]

The expressive power of GNNs can be improved by bootstrapping multiple graphs via dropout - An idea that we explored 4 years back (https://t.co/8IpRcQBeE4). Interesting to see new theory to support this (https://t.co/brOguaLFHY). Really wish they atleast cited us!! @RUSH1L

[Deepta Rajan @deepdanscience]

@savvyRL @anirudh3 drat! I thought of this same Hinge analogy :D

[Ziad Obermeyer @oziadias]

I spend a lot of “research” time pleading for access to health data

@m_sendhil and I co-founded a new nonprofit, @NightingaleOS, so you don’t have to

We link medical imaging data + ground truth outcomes, and make it available—free!

Launching tomorrow at #NeurIPS2021

[ASU SenSIP @asusensip]

Congratulations to @jjayaram7, Vivek & the entire team for their collaborative research on Deep Inversion Methods presented at the @NeurIPSConf. @AsuEnergy Ph.D student @VivekSivaraman1 presented the paper last Friday.
@Livermore_Lab
@deepdanscience

[Akash Srivastava @variational_i]

We are hiring research interns (summer 2022, PhD students only)
@MITIBMLab to work in areas such as contrastive learning, density ratio estimation, generative models and tabular data synthesis.
Please DM me your CV if you are interested. #internship

[Michal Rosen-Zvi @michal_zvi]

Do you like data challenges that can push the limits on how #ai impact #care? You are welcome to participate in the two challenges we just launched! You can learn from our own experience in participation in such challenge - see our paper at @NatMachIntell https://t.co/yKvnqvomiU

[Deepta Rajan @deepdanscience]

@Anuradha_D_18 Brilliant! Congratulations Anu!🥳

[Deepta Rajan @deepdanscience]

Meeting my fav collaborator after months & celebrating our #Neurips2022 paper on Explainable AI! 🥳 https://t.co/1r1rW2hVoe Checkout our work on counterfactual generation using deep inversion.

Grateful to be a part of this team @jjayaram7 @VivekSivaraman1 join us next time.🙌

[Jay Thiagarajan @jjayaram7]

Interested in designing counterfactual generators for deep models without access to source data or pre-trained generative models? Check out our #Neurips2022 paper that introduces DISC, a deep inversion technique for this problem. 2/5
https://t.co/Qsioy49iiH

[Deepta Rajan @deepdanscience]

@DrHughHarvey could we pique your interest with our calibration-based counterfactual explainers? 🙂
https://t.co/EmABmazVyO

[Talia Ringer 🕊🪬 @TaliaRinger]

"Ideas are free/cheap, but implementing them is the real work" is just a way of devaluing the work of people who are very good at generating ideas

[Rosanne Liu @savvyRL]

Earlier this summer Krystal and I are appointed as ICLR 2022 DEI chairs. Right away we started planning something tangible and actionable to *really* help broaden the ICLR participation pool.

Hence the birth of CoSubmitting Summer (CSS) program:
https://t.co/hBz375qB4b

1/

[Deepta Rajan @deepdanscience]

@bkailkhu @Livermore_Comp Congratulations! 🙂

P.S. - I work with Chaitanya.. small world! 🙌

[Deepta Rajan @deepdanscience]

😂 this thread! these billionaires!

[Sim Kern @sim_kern]

If any of you are under the impression that our billionaires might succeed in "escaping" to space, while the world burns, let me put those fears to rest with what I know from being the spouse of a NASA flight controller. 🧵