Results 91 to 100 of about 6,527,322 (289)
Advanced Functional Materials, EarlyView.An all‐in‐one analog AI accelerator is presented, enabling on‐chip training, weight retention, and long‐term inference acceleration. It leverages a BEOL‐integrated CMO/HfOx ReRAM array with low‐voltage operation (<1.5 V), multi‐bit capability over 32 states, low programming noise (10 nS), and near‐ideal weight transfer.
Donato Francesco Falcone +11 more
wiley +1 more source
Episodic Clustering of Data Streams Using a Topology-Learning Neural Network [PDF]
, 2012 Tscherepanow M, Kühnel S, Riechers S. Episodic Clustering of Data Streams Using a Topology-Learning Neural Network. In: Lemaire V, Lamirel J-C, Cuxac P, eds. Proceedings of the ECAI Workshop on Active and Incremental Learning (AIL).
Lamirel, Jean-Charles +5 more
core
Balanced Contrast Class‐Incremental Learning
CAAI Transactions on Intelligence TechnologyContinual learning aims to empower a model to learn new tasks continuously while reducing forgetting to retain previously learnt knowledge. In the context of receiving streaming data that are not constrained by the independent and identically distributed
Shiqi Yu, Luojun Lin, Yuanlong Yu
doaj +1 more source
Hybrid-Based Machine Incremental Learning in K-Nearest Neighbor Heterogeneous Drifting Environment
Applied SciencesThe ability to continuously learn over time by incorporating new information while holding onto previously acquired expertise is known as incremental learning (IL).
Japheth Otieno Ondiek +2 more
doaj +1 more source
Learning Automata Based Incremental Learning Method for Deep Neural Networks
IEEE Access, 2019 Deep learning methods have got fantastic performance on lots of large-scale datasets for machine learning tasks, such as visual recognition and neural language processing. Most of the progress on deep learning in recent years lied on supervised learning,
Haonan Guo +3 more
doaj +1 more source
Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning
17 pages, 6 figures, 6 tables, ECCV 2024 ...
Min-Yeong Park +2 more
openaire +4 more sources
Learning Boolean Functions Incrementally [PDF]
, 2012 Classical learning algorithms for Boolean functions assume that unknown targets are Boolean functions over fixed variables. The assumption precludes scenarios where indefinitely many variables are needed. It also induces unnecessary queries when many variables are redundant.
Yu-Fang Chen 0001, Bow-Yaw Wang
openaire +1 more source
Advanced Functional Materials, EarlyView.Monolithic UV‐ozone oxidation of Ta forms an ultrathin Ta2O5/TaOx bilayer enabling resistive switching with a vertical defect gradient. A stoichiometric surface layer over an oxygen‐deficient sublayer promotes localized filament nucleation near the top interface, enabling low‐voltage operation, and reduced cycle‐to‐cycle variability.
Seunghoon Yang +11 more
wiley +1 more source
Robust and Adaptive Incremental Learning for Varying Feature Space
IEEE AccessReal-world multiple or streaming tabular datasets, such as electronic health records from various sources and internet-of-things data generated from different devices, typically exhibit varied feature spaces depending on the datasets. Batch-mode learning
Cheol Ho Kim +3 more
doaj +1 more source
Advanced Functional Materials, EarlyView.A defect‐engineered Ag/Gd2O3:Nb2O5/Pt rare earth composite oxide memristor enables stable multilevel reservoir states through pulse driven conductance modulation. Experimentally measured device responses are incorporated into a device aware reservoir computing framework for CIFAR‐100 image classification, highlighting the potential of rare earth ...
Hammad Ghazanfar +9 more
wiley +1 more source