Results 91 to 100 of about 151,060 (281)

Sleep prevents catastrophic forgetting in spiking neural networks by forming joint synaptic weight representations [PDF]

, 2022
Artificial neural networks overwrite previously learned tasks when trained sequentially, a phenomenon known as catastrophic forgetting. In contrast, the brain learns continuously, and typically learns best when new training is interleaved with periods of
Delanois, Jean Erik
core   +1 more source

Challenges and strategies toward next‐generation high‐performance flexible and printable thin‐film transistors

FlexMat, EarlyView.
This review explores recent progress in printing strategies such as inkjet, screen, liquid metal, and roll to roll (R2R) methods and their roles in fabricating flexible TFTs. Device architectures are examined with emphasis on printed components and their influence on performance and stability.
Xia Zhao, Zhongqing Zeng, Zeyu Hu, Jaekyun Kim, Jidong Jin, Wensi Cai, Zhigang Zang   +6 more
wiley   +1 more source

Heating the Inflation Inequality in Greece

International Journal of Finance &Economics, EarlyView.
ABSTRACT The aim of the current study is twofold. First, we assess the household inflation inequality in Greece not only across different income groups but also across other households' social and economic characteristics, such as occupational status and household composition, among others.
Stavros Degiannakis, Panagiotis Delis, George Filis   +2 more
wiley   +1 more source

Dynamic Priority Replay and Boundary-Aware Distillation for Remote Sensing Scene Domain Incremental Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The continuous growth of remote sensing imagery introduces substantial distribution discrepancies between previously observed and newly acquired domains, making remote sensing scene classification models susceptible to catastrophic forgetting during ...
Jian Hu, Xue Li
doaj   +1 more source

Conditions for Catastrophic Forgetting in Multilingual Translation

Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
Fine-tuning multilingual foundation models on specific languages often induces catastrophic forgetting, degrading performance on languages unseen in fine-tuning. While this phenomenon is widely-documented, the literature presents fragmented results about when forgetting occurs.
Danni Liu, Jan Niehues
openaire   +2 more sources

Organic neuromorphic optoelectronic sensing materials, intelligent devices, and bionic systems

InfoMat, EarlyView.
Due to the excellent performance and biocompatibility, organic neuromorphic photoelectric sensing technology is regarded as a highly promising research field. In this review, Liu et al. summarize the recent advances in related materials, devices, and system integration.
Yu‐ang Liu, Guocai Liu, Lang Jiang, Yunqi Liu, Yunlong Guo   +4 more
wiley   +1 more source

The Governor Architecture: Avoiding Catastrophic Forgetting in Robot Learning [PDF]

, 2004
The governor architecture is a new method for avoiding catatrophic forgetting in neural networks that is particularly useful in online robot learn- ing.
Meeden, Lisa, Blank, Doug, Strober, Jeremy   +2 more
core   +1 more source

LaGu-RCL: Language-Guided Resolution-Continual Learning for Semantic Segmentation of Remote Sensing Images

Remote Sensing
Remote sensing image semantic segmentation faces substantial challenges in training and transferring models across images with varying resolutions. This issue can be effectively mitigated by continuously learning knowledge derived from new resolutions ...
Penglong Li, Zezhong Ma, Haifeng Li, Zhenyang Huang   +3 more
doaj   +1 more source

Overcoming catastrophic forgetting in neural networks

CoRR
Catastrophic forgetting is the primary challenge that hinders continual learning, which refers to a neural network ability to sequentially learn multiple tasks while retaining previously acquired knowledge. Elastic Weight Consolidation, a regularization-based approach inspired by synaptic consolidation in biological neural systems, has been used to ...
Brandon Shuen Yi Loke, Filippo Quadri, Gabriel Vivanco, Maximilian Casagrande, Saúl Fenollosa   +4 more
openaire   +3 more sources

Coping Practices of Small‐ and Medium‐Sized Enterprises Facing Power Asymmetry in Digital Platform Business

Strategic Change, EarlyView.
ABSTRACT Digital platform (DP) enterprises have risen to the top of the global economy by inverting traditional business models. They earn money through matchmaking, transaction facilitation, and efficient orchestration of other stakeholders' resources.
Lukas R. G. Fitz, Jochen Scheeg
wiley   +1 more source