Results 141 to 150 of about 72,144 (311)
Advanced Intelligent Systems, EarlyView.This study proposes a hardware‐efficient training methodology for crossbar arrays mapped with convolutional kernels in distributed computing systems. The approach is robust to variations in analog devices, minimizes disturbances during parallel writing operations, reduces stress on hardware, and accelerates the training process.
Jaehyeon Kang +3 more
wiley +1 more source
On a subgroup of the group of multiplicative arithmetic functions [PDF]
, 1975 Timothy B. Carroll, A. A. Gioia
openalex +1 more source
Transformation of arithmetic functions
Duke Mathematical Journal, 1973 Carlitz, L., Subbarao, M. V.
openaire +2 more sources
Improving Long‐Term Glucose Prediction Accuracy with Uncertainty‐Estimated ProbSparse‐Transformer
Advanced Intelligent Systems, EarlyView.Wearable devices collect blood glucose and other physiological data, which serve as inputs to the prediction model. After data embedding, a structure utilizing ProbSparse self‐attention and a one‐step generative head within a Transformer‐based model is introduced, which is concurrently designed for deployment on edge devices, enabling real‐time ...
Wei Huang +5 more
wiley +1 more source
Desirable floating-point arithmetic and elementary functions for numerical computation [PDF]
, 1978 D. E. Hull
openalex +1 more source
Symbolic Reservoir Computing within Memristive Crossbar Arrays as a Cellular Automata
Advanced Intelligent Systems, EarlyView.In quest of a neuro‐symbolic system with both strong intelligent computing capability and better explainability, a memristor crossbar array‐based cellular automata (symbolic model) for reservoir computing (neural network) is proposed and experimentally demonstrated using an algorithm–hardware codesign approach.
Yunpeng Guo +8 more
wiley +1 more source
Kolmogorov–Arnold Network for Transistor Compact Modeling
Advanced Intelligent Systems, EarlyView.This work introduces Kolmogorov–Arnold network (KAN) for the transistor—an architecture that integrates interpretability with high precision in physics‐based function modeling. The results reveal that despite achieving superior prediction accuracy for critical figures of merit, KAN demonstrates unique inherent challenges for transistor modeling ...
Rodion Novkin, Hussam Amrouch
wiley +1 more source
On the structure of certain basic sequences associated with an arithmetic function [PDF]
, 1971 Donald L. Goldsmith
openalex +1 more source
Mapping Postictal Aphasia through Signal Complexity: A Stereo‐Electroencephalography Study
Annals of Neurology, EarlyView.Objective The postictal period provides an opportunity to investigate the pathophysiology underlying aphasia and recovery following epileptic seizures. This study examines postictal aphasia in stereo‐electroencephalography (SEEG)‐explored patients to identify brain regions associated with task‐specific language deficits using signal complexity analysis.
Ionuț‐Flavius Bratu +6 more
wiley +1 more source