Alina Bialkowski
YOU?
Author Swipe
View article: Machine Unlearning for Streaming Forgetting
Machine Unlearning for Streaming Forgetting Open
Machine unlearning aims to remove knowledge of the specific training data in a well-trained model. Currently, machine unlearning methods typically handle all forgetting data in a single batch, removing the corresponding knowledge all at on…
View article: Supporting Data-Frame Dynamics in AI-assisted Decision Making
Supporting Data-Frame Dynamics in AI-assisted Decision Making Open
High stakes decision-making often requires a continuous interplay between evolving evidence and shifting hypotheses, a dynamic that is not well supported by current AI decision support systems. In this paper, we introduce a mixed-initiativ…
View article: Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models Open
Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have e…
View article: Clinical electromagnetic brain scanner
Clinical electromagnetic brain scanner Open
View article: Markerless motion capture provides accurate predictions of ground reaction forces across a range of movement tasks
Markerless motion capture provides accurate predictions of ground reaction forces across a range of movement tasks Open
Measuring or estimating the forces acting on the human body during movement is critical for determining the biomechanical aspects relating to injury, disease and healthy ageing. In this study we examined whether quantifying whole-body moti…
View article: CaMU: Disentangling Causal Effects in Deep Model Unlearning
CaMU: Disentangling Causal Effects in Deep Model Unlearning Open
Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing forg…
View article: Training Universal Deep-Learning Networks for Electromagnetic Medical Imaging Using a Large Database of Randomized Objects
Training Universal Deep-Learning Networks for Electromagnetic Medical Imaging Using a Large Database of Randomized Objects Open
Deep learning has become a powerful tool for solving inverse problems in electromagnetic medical imaging. However, contemporary deep-learning-based approaches are susceptible to inaccuracies stemming from inadequate training datasets, prim…
View article: Enlarging the model of the human at the heart of human-centered AI: A social self-determination model of AI system impact
Enlarging the model of the human at the heart of human-centered AI: A social self-determination model of AI system impact Open
Increasing awareness of the harms that artificial intelligence (AI) systems can cause has inspired a movement towards creating more human-centered AI (HCAI). One way in which AI systems can be made more human-centered is by focusing on the…
View article: Stroke Localization Using Multiple Ridge Regression Predictors Based on Electromagnetic Signals
Stroke Localization Using Multiple Ridge Regression Predictors Based on Electromagnetic Signals Open
Localizing stroke may be critical for elucidating underlying pathophysiology. This study proposes a ridge regression–meanshift (RRMS) framework using electromagnetic signals obtained from 16 antennas placed around the anthropomorphic head …
View article: Words Can Be Confusing: Stereotype Bias Removal in Text Classification at the Word Level
Words Can Be Confusing: Stereotype Bias Removal in Text Classification at the Word Level Open
Text classification is a widely used task in natural language processing. However, the presence of stereotype bias in text classification can lead to unfair and inaccurate predictions. Stereotype bias is particularly prevalent in words tha…
View article: Where is the human in human-centered AI? Insights from developer priorities and user experiences
Where is the human in human-centered AI? Insights from developer priorities and user experiences Open
Human-centered artificial intelligence (HCAI) seeks to shift the focus in AI development from technology to people. However, it is not clear whether existing HCAI principles and practices adequately accomplish this goal. To explore whether…
View article: Case Report: Preliminary Images From an Electromagnetic Portable Brain Scanner for Diagnosis and Monitoring of Acute Stroke
Case Report: Preliminary Images From an Electromagnetic Portable Brain Scanner for Diagnosis and Monitoring of Acute Stroke Open
Introduction: Electromagnetic imaging is an emerging technology which promises to provide a mobile, and rapid neuroimaging modality for pre-hospital and bedside evaluation of stroke patients based on the dielectric properties of the tissue…
View article: Brain Injury Localization in Electromagnetic Imaging using Symmetric Crossing Lines Method
Brain Injury Localization in Electromagnetic Imaging using Symmetric Crossing Lines Method Open
To avoid death or disability, patients with brain injury should undertake a diagnosis at the earliest time and accept frequent monitoring after starting any medical intervention. This paper presents a novel approach to localize brain injur…
View article: Characterizing Multi-Agent Team Behavior from Partial Team Tracings: Evidence from the English Premier League
Characterizing Multi-Agent Team Behavior from Partial Team Tracings: Evidence from the English Premier League Open
Real-world AI systems have been recently deployed which can automatically analyze the plan and tactics of tennis players. As the game-state is updated regularly at short intervals (i.e. point-level), a library of successful and unsuccessfu…
View article: The multi-camera surveillance database: for the task of person re-identification
The multi-camera surveillance database: for the task of person re-identification Open