Examining the impact of cue similarity and fear learning on perceptual tuning
Scientific Reports, 2023 Past research on the effects of associative aversive learning on discrimination acuity has shown mixed results, including increases, decreases, and no changes in discrimination ability.
Jonas Zaman +4 more
doaj +1 more source
Learning to live with discrimination
European Journal for Research on the Education and Learning of Adults, 2023 Otherness is one issue that comes up when discussing migration, and when it comes to asylum seeking in Europe, the topic of discrimination is a pivotal one also due to the rise of nationalistic political parties in the last few years.
Darasimi Oshodi
doaj +1 more source
Bigfin reef squid demonstrate capacity for conditional discrimination and projected future carbon dioxide levels have no effect on learning capabilities [PDF]
PeerJ, 2020 Anthropogenic carbon dioxide (CO2) emissions are being absorbed by the oceans, a process known as ocean acidification, and risks adversely affecting a variety of behaviours in a range of marine species, including inhibited learning in some fishes ...
Blake L. Spady, Sue-Ann Watson
doaj +2 more sources
Fairness in Semi-Supervised Learning: Unlabeled Data Help to Reduce Discrimination [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2020 A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models ...
Tao Zhang +5 more
semanticscholar +1 more source
Transfer in Rule-Based Category Learning Depends on the Training Task. [PDF]
PLoS ONE, 2016 While learning is often highly specific to the exact stimuli and tasks used during training, there are cases where training results in learning that generalizes more broadly.
Florian Kattner +2 more
doaj +1 more source
Maintaining Discrimination and Fairness in Class Incremental Learning [PDF]
Computer Vision and Pattern Recognition, 2019 Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting.
Bowen Zhao +4 more
semanticscholar +1 more source
Visual Analysis of Discrimination in Machine Learning [PDF]
IEEE Transactions on Visualization and Computer Graphics, 2020 The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning.
Qianwen Wang +5 more
semanticscholar +1 more source
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection [PDF]
Knowledge Discovery and Data Mining, 2023 Time series anomaly detection is critical for a wide range of applications. It aims to identify deviant samples from the normal sample distribution in time series. The most fundamental challenge for this task is to learn a representation map that enables
Yiyuan Yang +4 more
semanticscholar +1 more source
Discriminately decreasing discriminability with learned image filters [PDF]
2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012 In machine learning and computer vision, input images are often filtered to increase data discriminability. In some situations, however, one may wish to purposely decrease discriminability of one classification task (a "distractor" task), while simultaneously preserving information relevant to another (the task-of-interest): For example, it may be ...
Jacob Whitehill, Javier R. Movellan
openaire +3 more sources
Associative learning shapes visual discrimination in a web-based classical conditioning task
Scientific Reports, 2021 Threat detection plays a vital role in adapting behavior to changing environments. A fundamental function to improve threat detection is learning to differentiate between stimuli predicting danger and safety. Accordingly, aversive learning should lead to
Yannik Stegmann +3 more
doaj +1 more source