Zobrazeno 1 - 10
of 750
pro vyhledávání: '"Junier, P."'
We introduce Dynamic Information Sub-Selection (DISS), a novel framework of AI assistance designed to enhance the performance of black-box decision-makers by tailoring their information processing on a per-instance basis. Blackbox decision-makers (e.
Externí odkaz:
http://arxiv.org/abs/2410.23423
Autor:
Li, Yang, Oliva, Junier
Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and further inf
Externí odkaz:
http://arxiv.org/abs/2410.03915
Autor:
Li, Yang, Oliva, Junier
Many real-world situations allow for the acquisition of additional relevant information when making decisions with limited or uncertain data. However, traditional RL approaches either require all features to be acquired beforehand (e.g. in a MDP) or
Externí odkaz:
http://arxiv.org/abs/2410.03892
Anomaly detection and localization in medical imaging remain critical challenges in healthcare. This paper introduces Spatial-MSMA (Multiscale Score Matching Analysis), a novel unsupervised method for anomaly localization in volumetric brain MRIs. Bu
Externí odkaz:
http://arxiv.org/abs/2407.00148
Expansive Matching of Experts (EMOE) is a novel method that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty based rejection on out-of-distribution (OOD) points. We propose an expansive data augmentation
Externí odkaz:
http://arxiv.org/abs/2406.01825
Medical records often consist of different modalities, such as images, text, and tabular information. Integrating all modalities offers a holistic view of a patient's condition, while analyzing them longitudinally provides a better understanding of d
Externí odkaz:
http://arxiv.org/abs/2403.12211
Voice conversion (VC) aims at altering a person's voice to make it sound similar to the voice of another person while preserving linguistic content. Existing methods suffer from a dilemma between content intelligibility and speaker similarity; i.e.,
Externí odkaz:
http://arxiv.org/abs/2308.06382
We propose Gumbel Noise Score Matching (GNSM), a novel unsupervised method to detect anomalies in categorical data. GNSM accomplishes this by estimating the scores, i.e. the gradients of log likelihoods w.r.t.~inputs, of continuously relaxed categori
Externí odkaz:
http://arxiv.org/abs/2304.03220
Publikováno v:
Front. Microbiol. 14:1192831 (2023)
DNA supercoiling is central to many fundamental processes of living organisms. Its average level along the chromosome and over time reflects the dynamic equilibrium of opposite activities of topoisomerases, which are required to relax mechanical stre
Externí odkaz:
http://arxiv.org/abs/2303.10819
We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes acquisition costs whilst still yielding accurate predictions. The AFA fr
Externí odkaz:
http://arxiv.org/abs/2302.13960