Continual learning in medical image analysis: A survey DOI

X.B. Wu,

Zhe Xu, K.Y. Tong

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 182, P. 109206 - 109206

Published: Sept. 26, 2024

Language: Английский

A Comprehensive Survey of Continual Learning: Theory, Method and Application DOI
Liyuan Wang, Xingxing Zhang, Hang Su

et al.

IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal Year: 2024, Volume and Issue: 46(8), P. 5362 - 5383

Published: Feb. 26, 2024

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems develop themselves adaptively. In general sense, learning is explicitly limited by catastrophic forgetting, where new task usually results in dramatic performance drop of the old tasks. Beyond this, increasingly numerous advances have emerged recent years that largely extend understanding application learning. The growing widespread interest this direction demonstrates realistic significance well complexity. work, we present comprehensive survey seeking bridge basic settings, theoretical foundations, representative methods, practical applications. Based on existing empirical results, summarize objectives ensuring proper stability-plasticity trade-off adequate intra/inter-task generalizability context resource efficiency. Then provide state-of-the-art elaborated taxonomy, extensively analyzing how strategies address they are adapted particular challenges various Through in-depth discussion promising directions, believe such holistic perspective can greatly facilitate subsequent exploration field beyond.

Language: Английский

Citations

179
An improved convolutional neural network for predicting porous media permeability from rock thin sections DOI
Shuo Zhai, Shaoyang Geng, Chengyong Li

et al.

Gas Science and Engineering, Journal Year: 2024, Volume and Issue: 127, P. 205365 - 205365

Published: May 31, 2024

Language: Английский

Citations

9
Continual learning for energy management systems: A review of methods and applications, and a case study DOI Creative Commons
Aya Nabil Sayed, Yassine Himeur, Iraklis Varlamis

et al.

Applied Energy, Journal Year: 2025, Volume and Issue: 384, P. 125458 - 125458

Published: Feb. 10, 2025

Language: Английский

Citations

1
Multimodal Artificial Synapses for Neuromorphic Application DOI Creative Commons
Runze Li, Zengji Yue, Haitao Luan

et al.

Research, Journal Year: 2024, Volume and Issue: 7

Published: Jan. 1, 2024

The rapid development of neuromorphic computing has led to widespread investigation artificial synapses. These synapses can perform parallel in-memory functions while transmitting signals, enabling low-energy and fast intelligence. Robots are the most ideal endpoint for application In human nervous system, there different types sensory input, allowing signal preprocessing at receiving end. Therefore, anthropomorphic intelligent robots requires not only an intelligence system as brain but also combination multimodal multisensory sensing, including visual, tactile, olfactory, auditory, taste. This article reviews working mechanisms with stimulation response modalities, presents their use in various tasks. We aim provide researchers this frontier field a comprehensive understanding

Language: Английский

Citations

6
Experimental study of an integrated aluminum flat plate heat pipe for lightweight thermal management in electronic devices DOI
Jingjing Bai, Yiming Li,

Yincai Zhao

et al.

Applied Thermal Engineering, Journal Year: 2024, Volume and Issue: 257, P. 124332 - 124332

Published: Sept. 6, 2024

Language: Английский

Citations

6
Human-AI collaboration by design DOI Creative Commons

Binyang Song,

Qihao Zhu,

Jianxi Luo

et al.

Proceedings of the Design Society, Journal Year: 2024, Volume and Issue: 4, P. 2247 - 2256

Published: May 1, 2024

Abstract Human-AI collaboration (HAIC) is a promising strategy to transform engineering design and innovation, yet how artificial intelligence (AI) boost HAIC remains unclear. Accordingly, this paper provides new, unified, comprehensive scheme for classifying AI roles. On basis, we develop an framework that outlines expected capabilities, interactive attributes, trust enablers across various scenarios, offering guidance integrating into human teams effectively. We also discuss current advancements, challenges, prospects future research.

Language: Английский

Citations

5
Performance enhancement of artificial intelligence: A survey DOI
Moez Krichen, Mohamed S. Abdalzaher

Journal of Network and Computer Applications, Journal Year: 2024, Volume and Issue: unknown, P. 104034 - 104034

Published: Sept. 1, 2024

Language: Английский

Citations

5
Continual learning and catastrophic forgetting DOI
Gido M. van de Ven, Dhireesha Kudithipudi, Dhireesha Kudithipudi

et al.

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Language: Английский

Citations

4
Machine Memory Intelligence: Inspired by Human Memory Mechanisms DOI Creative Commons
Qinghua Zheng, Huan Liu,

Xiaoqing Zhang

et al.

Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Advancements in electronics cooling techniques: focus on graphene’s prospects, challenges, and future directions DOI
Mohammed Amer, Naseem Abbas

Journal of Thermal Analysis and Calorimetry, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 3, 2025

Language: Английский

Citations

0