Results 71 to 80 of about 24,131 (257)

Embedded Continual Learning for High-Energy Physics [PDF]

EPJ Web of Conferences
Neural Networks (NN) are often trained offline on large datasets and deployed on specialised hardware for inference, with a strict separation between training and inference.
Barbone Marco, Brown Christopher, Gaydadjiev Georgi, Maguire Thomas, Mieskolainen Mikael, Radburn-Smith Benjamin, Luk Wayne, Tapper Alexander   +7 more
doaj   +1 more source

Mathematics of Continual Learning

CoRR
Continual learning is an emerging subject in machine learning that aims to solve multiple tasks presented sequentially to the learner without forgetting previously learned tasks. Recently, many deep learning based approaches have been proposed for continual learning, however the mathematical foundations behind existing continual learning methods remain
Liangzu Peng, René Vidal
openaire   +2 more sources

Engineering Neuronal Network Connectivity Through Precise and Scalable Electrical Modulation

Advanced Science, EarlyView.
This study presents a scalable all‐electrical method for precise neuronal‐circuit reconfiguration based on high‐density microelectrode arrays. By employing biologically inspired plasticity rules, targeted connectivity changes were successfully induced and quantified across diverse neuronal preparations.
Sreedhar S. Kumar, Yannaël Bossard, Rachel Sava, Tobias Gänswein, Lorenca Sadiraj, Jean‐Samuel Dupré, Manuel Schröter, J. Gray Camp, Fernando Cardes, Julian Bartram, Andreas Hierlemann   +10 more
wiley   +1 more source

How Advanced Artificial Intelligence Technologies Shape Drug–Drug and Drug–Target Interaction Modeling

Advanced Science, EarlyView.
This review explores the convergence of artificial intelligence technologies in modeling drug–drug and drug–target interactions. By evaluating advanced feature engineering, architectural innovations, and learning paradigms reveals shared evolutionary trends and critical challenges, such as cold‐start settings and shortcut learning.
Xin Sun, Tong Wang
wiley   +1 more source

Reconfigurable Selector‐Only Memory (SOM) for Scalable Neuromorphic Computing

Advanced Science, EarlyView.
ABSTRACT Highly scalable reconfigurable neuromorphic devices are critical for addressing continual‐learning challenges in artificial intelligence. However, the scalability of existing reconfigurable devices is severely constrained by limited operating margins and insufficient process maturity.
Jin‐Yu Wen, Chuan‐Qi Yi, Ya‐Ru Zhang, Bin‐Hao Wang, Zi‐Xuan Liu, Chun‐Yu Zhou, Hao Tong, Xiang‐Shui Miao   +7 more
wiley   +1 more source

Privacy-Preserving Continual Federated Clustering via Adaptive Resonance Theory

IEEE Access
With the increasing importance of data privacy protection, various privacy-preserving machine learning methods have been proposed. In the clustering domain, various algorithms with a federated learning framework (i.e., federated clustering) have been ...
Naoki Masuyama, Yusuke Nojima, Yuichiro Toda, Chu Kiong Loo, Hisao Ishibuchi, Naoyuki Kubota   +5 more
doaj   +1 more source

Modular-Relatedness for Continual Learning

, 2022
We realized one conclusion in the submission is erroneous and disconnected from the results shown in one theorem is.
Ammar Shaker, Francesco Alesiani, Shujian Yu   +2 more
openaire   +2 more sources

Pressure‐Induced Drift Artifacts in Stretchable Liquid Metal ThinFilm Electrocardiogram Electrodes

Advanced Science, EarlyView.
A stretchable LM electrode integrated with a strain sensor enables in situ quantitative investigation of drift artifact and skin deformation. This reveals the significance of pressure‐induced drift artifact and its intimate relationship with the skin potential model.
Ding Li, Zi‐Gan Xu, Zhi‐Kang Chen, Shuo‐Yan Xu, Jia‐Yi Cui, Si‐Yuan Wo, Zi‐Xu Wang, Yi‐Kun Liu, Jia‐Ju Yin, Hou‐Fang Liu, Xiao‐Ming Wu, Lu‐Qi Tao, Yi Yang, Tian‐Ling Ren   +13 more
wiley   +1 more source

Online Continual Physics-Informed Learning for Quadrotor State Estimation Under Wind-Induced Disturbances

Aerospace
Accurate state estimation for quadrotors under wind-induced disturbances remains a critical challenge in dynamic outdoor environments. Existing model-based and data-driven approaches often struggle with real-time adaptation and catastrophic forgetting ...
Yanhui Liu, Shuopeng Wang, Junhua Shi, Lina Hao   +3 more
doaj   +1 more source

Exact Discrete Stochastic Simulation With Deep‐Learning‐Scale Gradient Optimization

Advanced Science, EarlyView.
A 203,796‐parameter gene regulatory network classifies handwritten digits with 98.4% accuracy using exact stochastic dynamics. The framework decouples forward simulation from backward differentiation, making continuous‐time Markov chain models compatible with deep‐learning optimization.
Jose M. G. Vilar, Leonor Saiz
wiley   +1 more source