Results 111 to 120 of about 151,060 (281)

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

Living Through a Changing Climate: Stress, Trauma, and Gendered Resilience Among Women in Coastal and Northern Ghana

Sustainable Development, EarlyView.
ABSTRACT Climate change is reshaping everyday life in Ghana through coastal erosion, flooding, erratic rainfall, water scarcity, extreme heat, and agricultural insecurity. This study examines how these changes produce stress, trauma, and gendered resilience among women in Salakope and Choggu Yapalsi, two climate‐vulnerable communities in coastal and ...
Jacob Kwakye
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

Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning. [PDF]

Front Neurorobot, 2023
Hafez MB, Immisch T, Weber T, Wermter S.
europepmc   +1 more source

Schools That Educate Students Who Transform Businesses and Change the World: The Transformative Role of Education for the Circular Economy

Sustainable Development, EarlyView.
ABSTRACT The linear economic model continues to intensify environmental degradation and resource depletion, yet education for the circular economy (ECE) remains underdeveloped, particularly within basic education and in the Global South. This study evaluates the feasibility and effectiveness of an ECE Programme grounded in active learning methodologies,
Maiara Lais Marcon, Simone Sehnem
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

TDG-LoRA: Token-Level Dynamic Gating for Mitigating Catastrophic Forgetting

IEEE Access
Parameter-efficient fine-tuning (PEFT), particularly Low-Rank Adaptation (LoRA), is widely used to adapt large language models (LLMs) to specialized downstream domains.
Shushan Zhu, Shangqing Huang, Xingyuan Chen   +2 more
doaj   +1 more source

A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost. [PDF]

Sci Adv, 2023
Zhang T, Cheng X, Jia S, Li CT, Poo MM, Xu B.   +5 more
europepmc   +1 more source

Overcoming Catastrophic Forgetting by Soft Parameter Pruning

CoRR, 2018
Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint distribution of parameters shared with all tasks.
Jian Peng 0009, Hao Jiang 0020, Zhuo Li, Enqiang Guo, Xiaohong Wan, Min Deng, Qing Zhu 0012, Haifeng Li 0007   +7 more
openaire   +3 more sources

Aftermath of the Forest Carbon Credit Crisis as Experienced by Restoration and Conservation Organisations

Sustainable Development, EarlyView.
ABSTRACT In 2023, The Guardian reported on several scientific studies denouncing the role of certain forest carbon credits in mitigating climate change. Subsequently, credit prices on the voluntary carbon market (VCM) plummeted—providing a quantitative indication of its impact.
Benjamin S. Thompson, Sara Löfqvist, Felicia H. M. Liu, Jack L. Harris   +3 more
wiley   +1 more source