#uncertaintyquantification

2023-11-02

Explaining model *predictions* is all well and good – but what about model *uncertainty*?

Pleased to announce that our paper on information theoretic Shapley values will be presented at #NeurIPS2023.

Joint work with David Watson, Josh O’Hara, Richard Mudd, and Ido Guy.

arxiv.org/abs/2306.05724

#NeurIPS #xai #UncertaintyQuantification #machinelearning

2023-08-11

The list of accepted papers of our #ICCV workshop on #UncertaintyQuantification for #ComputerVision is out!

Check out: uncv2023.github.io/papers/

2022-12-29

🚀 #AWS Fortuna is skyrocketing! 🚀 Just a few days, and so many GitHub stars and forks! ⭐️

Fortuna supports #ConformalPrediction, #BayesianInference and other methods for #UncertaintyQuantification in #DeepLearning.

Try it out and let us know!
github.com/awslabs/fortuna

In collaboration with @cedapprox, @andrewgwils and team.

#uncertainty #neuralnetworks #bayesian #conformal #calibration #jax #flax #python #opensource #library #machinelearning #ai

Cédric Archambeaucedapprox@sigmoid.social
2022-12-20

Today, we open sourced Fortuna (github.com/awslabs/fortuna) a library for uncertainty quantification.
Deep neural networks are often overconfident and do not know what they don’t know. Quantifying the uncertainty in the predictions they make will help deploy deep learning more responsibly and more safely.
#responsibleAI #ConformalPrediction #BayesianInference #UncertaintyQuantification #deeplearning #opensource

2022-11-21
Taylor W. Killiantw_killian@sigmoid.social
2022-11-07

Time for an #introduction?

I'm in the latter stages of my PhD at the University of Toronto (while sitting at MIT). My research focuses on the use of offline #ReinforcementLearning and #UncertaintyQuantification to assess risk and recommend decisions to avoid in safety-critical settings as well as the generalization of policies. I have a particular interest in #Healthcare challenges but am generally interested in all of RL.

Soon to be on the job market for Research Scientist positions!

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst