Results 91 to 100 of about 3,000 (250)

Unravelling Cascading Phenomena in Sociotechnical Systems: A Systematic Review and Modelling Framework

Systems Research and Behavioral Science, EarlyView.
ABSTRACT This article investigates the characterization of cascading phenomena within sociotechnical systems through a systematic review and the development of a conceptual modelling framework. Cascading phenomena, often described using terms such as ripple effect, domino effect, cascading failure, risk propagation and cascading effect, capture the far‐
Jiayao Li, Alexis Evain, Clara Le Duff, Tianyuan Zhang, David Panzoli, Audrey Fertier, Benoit Montreuil, Frederick Benaben   +7 more
wiley   +1 more source

EXACFS - A CIL Method to Mitigate Catastrophic Forgetting

Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing
Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary challenge. This paper introduces EXponentially Averaged Class-wise Feature Significance (EXACFS) to mitigate this issue
S. Balasubramanian 0001, M. Sai Subramaniam, Sai Sriram Talasu, Manepalli Pranav Phanindra Sai, Yedu Krishna P, Darshan Gera, Ravi Mukkamala   +6 more
openaire   +3 more sources

“Being Nice” as Modus Vivendi in Classrooms: A Collective Behavior Approach to Deviant Behavior in Primary Schools

Symbolic Interaction, EarlyView.
This study of first‐year primary school draws on Goffman's concept of “collective behavior” to examine how order is established and disrupted through the mutual adjustment of all participants' actions. We employed a multi‐method longitudinal design, using semi‐standardized observations and qualitative interviews with teachers and children at three ...
Doris Bühler‐Niederberger, Leon Dittmann, Claudia Schuchart   +2 more
wiley   +1 more source

Generalisable deep Learning framework to overcome catastrophic forgetting

Intelligent Systems with Applications
Generalisation across multiple tasks is a major challenge in deep learning for medical imaging applications, as it can cause a catastrophic forgetting problem.
Zaenab Alammar, Laith Alzubaidi, Jinglan Zhang, Yuefeng Li, Ashish Gupta, Yuantong Gu   +5 more
doaj   +1 more source

Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks

IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2019
Continual learning is the ability to acquire a new task or knowledge without losing any previously collected information. Achieving continual learning in artificial intelligence (AI) is currently prevented by catastrophic forgetting, where training of a ...
Irene Munoz-Martin, Stefano Bianchi, Giacomo Pedretti, Octavian Melnic, Stefano Ambrogio, Daniele Ielmini   +5 more
doaj   +1 more source

How weather got its words: a history of meteorological English – Part 2: the scientific age and beyond

Weather, EarlyView.
The English language is a gargantuan, gluttonous beast. It has become extraordinary in its powers of assimilation – such that we rarely consider the origins of the words we use. In this paper, we will shed light on these origins, including the Pontic–Caspian steppe, the British Empire and, of course, a TV show.
Kieran M. R. Hunt
wiley   +1 more source

Exploring Kolmogorov–Arnold Network Expansions in Vision Transformers for Mitigation of Catastrophic Forgetting in Continual Learning

Mathematics
Continual Learning (CL), the ability of a model to learn new tasks without forgetting previously acquired knowledge, remains a critical challenge in artificial intelligence. This is particularly true for Vision Transformers (ViTs) that utilize Multilayer
Zahid Ullah, Jihie Kim
doaj   +1 more source

Toward Understanding Catastrophic Forgetting in Continual Learning

CoRR, 2019
We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties of this sequence influence the error rates of continual learning algorithms trained on the sequence.
Cuong V. Nguyen, Alessandro Achille, Michael Lam, Tal Hassner, Vijay Mahadevan, Stefano Soatto   +5 more
openaire   +2 more sources

Robust Multi‐Source Batch Normalisation for Test‐Time Batch Adaptation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Test‐Time Batch Adaptation (TTBA) aims to adapt a pre‐trained source model to small, unlabelled target batches at test time. The TTBA methods focus on adapting the pre‐trained model or the target data in a one‐to‐one alignment paradigm. However, these one‐to‐one alignment paradigms assume that the source domain may share the same knowledge ...
Xinlin Xiao, Xiangtao Zheng, Jianhua Tao, Xiaoqiang Lu   +3 more
wiley   +1 more source

Exploring multi-granularity balance strategy for class incremental learning via three-way granular computing

Brain Informatics
Class incremental learning (CIL) is a specific scenario in incremental learning. It aims to continuously learn new classes from the data stream, which suffers from the challenge of catastrophic forgetting.
Yan Xian, Hong Yu, Ye Wang, Guoyin Wang
doaj   +1 more source