Dance n' Data for Science. Applied AI in Healthcare, Enterprise, and Manufacturing. Always ready to workout.
Joined June 2019
- Tweets149
- Following432
- Followers106
- Likes1.1K
Meeting my fav collaborator after months & celebrating our #Neurips2022 paper on Explainable AI! 🥳 arxiv.org/abs/2109.14274 Checkout our work on counterfactual generation using deep inversion.
Grateful to be a part of this team @jjayaram7 @VivekSivaraman1 join us next time.🙌
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
arxiv.org/abs/2109.14274
1
9
Key findings:
a) Consistency under weak data augmentation insufficient.
b) Mixup and Confidence Tempering regularization helps combat confirmation biases.
c) Self-Training with a noisy student network (distillation) by including pseudo-labeled data helps. 3/3
Our proposed small-data learning framework shows that using 85% lesser labeled data, we can build models that match performance of classifiers trained in a large-scale data setting.
We share tricks for handling limited labeled data, class imbalance and multiple conditions. 2/3
Thrilled to share that our work won the #BestPaperAward at the #SPIEMedicalImaging conference! 🥳 @SPIEtweets 👉arxiv.org/pdf/2005.02231.pdf
Congratulations! to the awesome sauce team led by @jjayaram7 🙌👏 alex karagyris,@follow_kashyap 1/3
#CollabFTW @IBMResearch @Livermore_Comp
We introduce “Reliability Plots” — a way to trade off between model autonomy and it’s accuracy in the real-world especially on test data when evaluating on patients we’ve never seen before.
1
2
So fun! looking great Anima...thanks for sharing :) Dancing is my coping mechanism too, and I've been taking some virtual bollywood classes --
youtube.com/watch?v=Wu2_5zvf…
4
Super excited to present our work on Pulmonary Embolism detection (arxiv.org/pdf/1910.02175.pdf) at NeurIPS ML4H, and Multimodal Clinical Time-Series analysis at WiML. @jjayaram7 @sam94katoch
#NeurIPS2019 #WiML
