Results 151 to 160 of about 484,117 (322)

Bubbles Acting as Micro End‐Effectors for Dexterous Manipulation and Sensing in Aqueous Environment

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
Inspired by bubbles, this article proposes a low‐cost method for multifunctional manipulation and sensing using microbubbles in aqueous environments. Bubbles are easily generated in situ, enabling the safe and adaptive handling of microobjects and sensing of microforces and surface textures.
Zichen Xu, Qingsong Xu
wiley   +1 more source

Investigation of Analog Memristor Characteristics for Hardware Synaptic Weight in Multilayer Neural Network

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
The systematic design of memristor‐based neural network is provided by analog conductance state parameters to accurately emulate the software‐based high‐resolution weight at discrete device level. The requirement of discrete analog conductance of memristor device is measured as ≈50 states with nonlinearity value of ≈0.142 within the deviation range of ...
Jingon Jang, Yoonseok Song, Sungjun Park
wiley   +1 more source

Accelerating Pinned Insect Specimen Digitization: A Deep Learning Pipeline for Future Collaborative Robots

open access: yesAdvanced Intelligent Systems, EarlyView.
The study presents a prototype novel workflow that utilizes artificial intelligence for the digitization of natural history collections, which would fit within a robotic‐integrated system. The work focuses on a collaborative‐robot (cobot) inspired workflow to digitize one of the largest collections housed at the Natural History Museum UK: pinned ...
Naifeng Zhang   +4 more
wiley   +1 more source

Selective Update for Hardware‐Friendly On‐Chip Training in Distributed Analog In‐Memory Computing Systems

open access: yesAdvanced 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

Home - About - Disclaimer - Privacy