Spuriosity didn't kill the classifier: Using invariant predictions to harness spurious features
To avoid failures on out-of-distribution data, recent works have sought to extract features that
have an invariant or stable relationship with the label across domains, discarding" spurious" …
have an invariant or stable relationship with the label across domains, discarding" spurious" …
Developing an artificial intelligence–based diagnostic model of headaches from a dataset of clinic patients' records
M Katsuki, Y Matsumori, S Kawamura… - … : The Journal of …, 2023 - Wiley Online Library
Objective We developed an artificial intelligence (AI)‐based headache diagnosis model
using a large questionnaire database from a headache‐specializing clinic. Background …
using a large questionnaire database from a headache‐specializing clinic. Background …
Calibration in deep learning: A survey of the state-of-the-art
C Wang - arXiv preprint arXiv:2308.01222, 2023 - arxiv.org
Calibrating deep neural models plays an important role in building reliable, robust AI
systems in safety-critical applications. Recent work has shown that modern neural networks …
systems in safety-critical applications. Recent work has shown that modern neural networks …
Hybrid AI-enhanced lightning flash prediction in the medium-range forecast horizon
M Cavaiola, F Cassola, D Sacchetti, F Ferrari… - Nature …, 2024 - nature.com
Traditional fully-deterministic algorithms, which rely on physical equations and mathematical
models, are the backbone of many scientific disciplines for decades. These algorithms are …
models, are the backbone of many scientific disciplines for decades. These algorithms are …
Automated machine learning: past, present and future
Automated machine learning (AutoML) is a young research area aiming at making high-
performance machine learning techniques accessible to a broad set of users. This is …
performance machine learning techniques accessible to a broad set of users. This is …
[HTML][HTML] Calibrating subjective data biases and model predictive uncertainties in machine learning-based thermal perception predictions
Abstract Heating, Ventilation, and Air Conditioning (HVAC) systems in large-scale buildings
often struggle to ensure satisfactory thermal comfort for diverse occupants while minimizing …
often struggle to ensure satisfactory thermal comfort for diverse occupants while minimizing …
Resilience-aware MLOps for AI-based medical diagnostic system
V Moskalenko, V Kharchenko - Frontiers in Public Health, 2024 - frontiersin.org
Background The healthcare sector demands a higher degree of responsibility,
trustworthiness, and accountability when implementing Artificial Intelligence (AI) systems …
trustworthiness, and accountability when implementing Artificial Intelligence (AI) systems …
Impact of preference noise on the alignment performance of generative language models
A key requirement in developing Generative Language Models (GLMs) is to have their
values aligned with human values. Preference-based alignment is a widely used paradigm …
values aligned with human values. Preference-based alignment is a widely used paradigm …
Methodology and evaluation in sports analytics: challenges, approaches, and lessons learned
There has been an explosion of data collected about sports. Because such data is extremely
rich and complex, machine learning is increasingly being used to extract actionable insights …
rich and complex, machine learning is increasingly being used to extract actionable insights …
Selection of powerful radio galaxies with machine learning
Context. The study of active galactic nuclei (AGNs) is fundamental to discern the formation
and growth of supermassive black holes (SMBHs) and their connection with star formation …
and growth of supermassive black holes (SMBHs) and their connection with star formation …