Results 241 to 250 of about 151,060 (281)

Social Diseases and Social Problems: An Islamic Framework for Cultural Awareness And Social Diagnosis

Sociological Inquiry, Volume 96, Issue 4, 2026.
Despite decades of policy interventions, the world suffers from profound social problems including drug abuse, family breakdown, and systemic injustice. The research problem is the persistent gap in existing sociological theories: objective criteria lacking for diagnosing social harm before it becomes visible.
Jilani Ben Touhami Meftah
wiley   +1 more source

Bias Calibration for Semi-Supervised Continual Learning. [PDF]

Sensors (Basel)
Ji Z, Jiao Z, Miao D, Tang C.
europepmc   +1 more source

A Closed‐Loop Framework for Inverse Design: Dynamic Training and Intelligent Optimization for Heterostructured Materials

Advanced Science, Volume 13, Issue 55, 5 October 2026.
To accelerate the inverse design of heterostructured metal matrix composites, a closed‐loop scientific machine learning framework integrates continual learning prediction with NSGA‐II‐PMCP optimization. The framework maps microstructural descriptors to strength, toughness, and modulus, expands high‐quality Pareto solutions, and guides experimentally ...
Zhiyan Zhong, Xueru Zheng, Xiao Zhou, Zhengheng Tao, Wan Han, Jingyi Pan, Dian Wu, Ning Gao, Lei Liu, Zhongyang Wang, Fanchao Meng, Tongxiang Fan   +11 more
wiley   +1 more source

Astrocyte-gated multi-timescale plasticity for online continual learning in deep spiking neural networks. [PDF]

Front Neurosci
Dong Z, He W.
europepmc   +1 more source

OD-ViTFScL: Asynchronous Few-Shot Continual Learning for Intelligent Process Monitoring and Fault Diagnosis in Petrochemical Plants. [PDF]

Sensors (Basel)
Oshidele O, Lin S.
europepmc   +1 more source

SynSAM: a hybrid synchronous learning framework with knowledge retention for prostate zonal segmentation leveraging the segment anything model. [PDF]

Med Biol Eng Comput
Krishnan C, Onuoha E, Hung A, Sung KH, Kim H.   +4 more
europepmc   +1 more source

Decoupling forgetting and preservation in federated unlearning via knowledge distillation. [PDF]

Sci Rep
Kwon H, Maeng JB, Kim DJ.
europepmc   +1 more source

Class-incremental few-shot underwater object detection framework. [PDF]

Sci Rep
Zhao X, Zhou B, Wang Y.
europepmc   +1 more source

PADP: progressive and adaptive data pruning for efficient incremental learning. [PDF]

Sci Rep
Duan B, Liu D, He Z, Zhou W, Miao S.
europepmc   +1 more source

Catastrophic forgetting and mode collapse in GANs

2020 International Joint Conference on Neural Networks (IJCNN), 2020
In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the discriminator.
Hoang Thanh-Tung, Truyen Tran 0001
openaire   +2 more sources