Published papers at TMLR · @tmlrpub
522 followers · 452 posts · Server sigmoid.social
On the Convergence and Calibration of Deep Learning with Differential Privacy
Zhiqi Bu, Hua Wang, Zongyu Dai, Qi Long
Action editor: Sebastian Stich.
Published papers at TMLR · @tmlrpub
520 followers · 446 posts · Server sigmoid.social
Finding Competence Regions in Domain Generalization
Jens Müller, Stefan T. Radev, Robert Schmier, Felix Draxler, Carsten Rother, Ullrich Koethe
Action editor: Hanwang Zhang.
#classifiers #Accuracy #classifier
New Submissions to TMLR · @tmlrsub
174 followers · 524 posts · Server sigmoid.social
Finding Competence Regions in Domain Generalization
#classifiers #Accuracy #classifier
JMLR · @jmlr
656 followers · 184 posts · Server sigmoid.social
'Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule', by Nikhil Iyer, V. Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu.
http://jmlr.org/papers/v24/21-0549.html
#training #accuracy #minima
Published papers at TMLR · @tmlrpub
511 followers · 341 posts · Server sigmoid.social
UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed...
Francisca Vasconcelos, Bobby He, Nalini M Singh, Yee Whye Teh
WIST Quotations · @WISTquote
44 followers · 486 posts · Server zirk.usA quotation from Confucius:
«««««
The one thing needed is the correction of terms. […] If terms be incorrect, then statements do not accord with facts; and when statements and facts do not accord, then business is not properly executed; when business is not properly executed, order and harmony do not flourish; when order and harmony do not flourish, then just…
»»»»»
Full quote, sourcing, notes:
https://wist.info/confucius/60124/
#quote #quotes #quotation #Accuracy #correction #definition
Andy King · @AtoAndyKing
101 followers · 73 posts · Server sigmoid.socialNew #ISBI2023 paper by Tareen Dawood:
https://arxiv.org/abs/2301.13296v1
We focus on the idea of #DeepLearning #uncertainty #calibration, i.e. improving the relationship between a classification model's #accuracy and #confidence.
We explore the idea of uncertainty-aware training -including calibration performance in the learning objective of the model - and also evaluate the calibration performance of evidential neural networks (ENNs).
#isbi2023 #deeplearning #uncertainty #calibration #Accuracy #confidence
Published papers at TMLR · @tmlrpub
489 followers · 152 posts · Server sigmoid.social
Hidden Heterogeneity: When to Choose Similarity-Based Calibration
Kiri L. Wagstaff, Thomas G Dietterich
#classifiers #classifier #Accuracy
New Submissions to TMLR · @tmlrsub
148 followers · 305 posts · Server sigmoid.social
UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography
NanoBookReview · @NanoBookReview
91 followers · 144 posts · Server zirk.usWhat should I #Read next? We're using #Approval #Voting, vote for as many as you like! Please #Vote and boost for visibility!
#ApprovalVoting is a #Simple, #Fast, #Accurate, #Easy, #Monotonic, #SpoilerFree Voting method we should be using for all our voting needs. But, this will have to do, for now.
#Books #Nonfiction #Literature #Learning #Poll #Polling #Reviews #VotingMethods #Accuracy #Participation #Satisfaction
#read #approval #voting #Vote #approvalvoting #simple #fast #accurate #easy #monotonic #spoilerfree #Books #nonfiction #literature #learning #poll #polling #reviews #votingmethods #Accuracy #participation #satisfaction
Cian Ó Muilleoir · @KinoEmm
59 followers · 149 posts · Server data-folks.masto.host
Can't find a non-bot #XKCD account on here but this #Accuracy #Precision matrix is just too good not to share.