Joost van Amersfoort
5 papers · 2019–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (13) π§ Keyword Pioneer π Conference Polyglot (4) π Interdisciplinary Bridge π£ Hot Topic Early Bird
π
Cross-Pollinator
(8)
π₯
Unstoppable
(5)
Conferences
NIPS (2)
CVPR (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
uncertainty quantification
(3)
out-of-distribution detection
(2)
bayesian active learning
(2)
epistemic uncertainty
(1)
deep learning
(1)
mutual information
(1)
feature space
(1)
greedy algorithm
(1)
treatment effect
(1)
aleatoric uncertainty
(1)
observational datum
(1)
deep ensemble
(1)
personalized treatment
(1)
gradient penalty
(1)
deterministic uncertainty quantification
(1)
rbf network
(1)
out of distribution detection
(1)
deterministic neural network
(1)
softmax model
(1)
softmax neural network
(1)
Papers
Deep Deterministic Uncertainty: A New Simple Baseline
CVPR 2023
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
ICLR 2022
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
NIPS 2021
Uncertainty Estimation Using a Single Deep Deterministic Neural Network
ICML 2020
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
NIPS 2019