Results 171 to 180 of about 851,945 (325)

Kolmogorov–Arnold Network for Transistor Compact Modeling

open access: yesAdvanced 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

Harnessing Nonidealities in Analog In‐Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems

open access: yesAdvanced Intelligent Systems, EarlyView.
This work harnesses nonidealities in analog in‐memory computing (IMC) by training physical neural networks modeled with ordinary differential equations. A differentiable spike‐time discretization accelerates training by 20× and reduces memory usage by 100×, enabling large IMC‐equivalent models to learn the CIFAR‐10 dataset.
Yusuke Sakemi   +5 more
wiley   +1 more source

Delaunay-Like Compact Equilibria in the Liquid Drop Model. [PDF]

open access: yesArch Ration Mech Anal
Del Pino M, Musso M, Zuniga A.
europepmc   +1 more source

BiT‐HyMLPKANClassifier: A Hybrid Deep Learning Framework for Human Peripheral Blood Cell Classification Using Big Transfer Models and Kolmogorov–Arnold Networks

open access: yesAdvanced Intelligent Systems, EarlyView.
This study presents BiT‐HyMLPKANClassifier, a novel hybrid deep learning framework for automated human peripheral blood cell classification. Model combines Big Transfer models with multilayer perceptron and efficient Kolmogorov–Arnold Network architectures, achieving over 97% accuracy.
Ömer Miraç KÖKÇAM, Ferhat UÇAR
wiley   +1 more source

A Robotic Urinary Bladder Enabling Volume Monitoring and Assisted Micturition

open access: yesAdvanced Intelligent Systems, EarlyView.
An implantable robotic bladder is presented that can store urine in an origami‐designed enclosure. An inductance sensing principle can monitor and transfer the urine volume in real‐time. It can actively expand based on the amount of urine collected from kidneys and apply on‐demand mechanical compression to assist urination.
Izadyar Tamadon   +4 more
wiley   +1 more source

From Droplet to Diagnosis: Spatio‐Temporal Pattern Recognition in Drying Biofluids

open access: yesAdvanced Intelligent Systems, EarlyView.
This article integrates machine learning (ML) with the spatio‐temporal evolution of biofluid droplets to reveal how drying and self‐assembly encode distinctive compositional fingerprints. By leveraging textural features and interpretable ML, it achieves robust classification of blood abnormalities with over 95% accuracy.
Anusuya Pal   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy