Results 141 to 150 of about 6,675,279 (300)

Directional Latent Hybridization: Beyond Random Noise in Physics‐Informed Generative Inverse Design of Nonlinear Metamaterials

Advanced Materials Technologies, EarlyView.
A physics‐informed generative framework introduces Directional Latent Hybridization (DLH) for the deterministic inverse design of nonlinear metamaterials. By hybridizing dominant traits from parent geometries in the latent space, DLH overcomes the instabilities of stochastic models to ensure high structural precision at high densities.
Semin Ahn, Jun Young Choi, Sung‐Hoon Ahn   +2 more
wiley   +1 more source

Toward Perception‐Native Electronic Skin: Bio‐Inspired In‐/Near‐Sensor and Neuromorphic Computing for Humanoid Robots

Advanced Materials Technologies, EarlyView.
Dense tactile streams from across the humanoid body converge on collide in a central wiring and data bottleneck. By relocating computation closer to and then into the skin itself, near‐ and in‐sensor architectures, together with neuromorphic computing, chart a path toward perception‐native electronic skin, in which the conversion of stimulus into ...
Mijin Kim, Chang‐Jae Beak, Jiyoung Park, Youngdo Jung, Sunjong Oh, Sin‐Hyung Lee, Bo‐Yeon Lee   +6 more
wiley   +1 more source

Whetstone Trained Spiking Deep Neural Networks to Spiking Neural Networks [PDF]

, 2019
A deep neural network is a non-spiking artificial neural network which uses multiple structured layers to extract features from the input. Spiking neural networks are another type of artificial neural network which closely mimic biology with time ...
Zhao, Jiajia
core  

Recent Advances in Transparent Microelectrode Device Architecture and Fabrication Strategies for Biomedical Applications

Advanced Materials Technologies, EarlyView.
Transparent microelectrode arrays enable simultaneous optical and electrical electrophysiology with high spatiotemporal resolution, allowing multimodal observations of dynamic biological systems. Advances in materials and device architectures improve device performance by addressing key trade‐offs between optical transparency, impedance, and ...
Michael Abraham Listyawan, Tran Bach Dang, Chi Cong Nguyen, Yee Lap Pong, Tianruo Guo, Thanh Nho Do, Hoang‐Phuong Phan   +6 more
wiley   +1 more source

Microscale 3D‐Printed Digital Strain Switches for Embedded Mechanical Computation

Advanced Materials Technologies, EarlyView.
Microscale 3D‐printed strain switches on flexible films convert deformation into native digital signals at geometry defined thresholds. A closed form model predicts switching from 3000 to 15 000 microstrain and is validated across 110 devices. Reliable ohmic closure and strain activated AND, OR, and XOR logic point toward low‐power mechanical ...
Regan Kubicek, Daniel Quinn, Gabriel Smith, Sarah Bergbreiter   +3 more
wiley   +1 more source

BIASNN: a biologically inspired attention mechanism in spiking neural networks for image classification

Scientific Reports
Spiking Neural Networks (SNNs), designed to more accurately model the brain’s neurobiological processes, have been proposed as energy-efficient alternatives to conventional Artificial Neural Networks (ANNs), which typically incur high computational and ...
Kevin Takala, Wachirawut Thamviset, Sartra Wongthanavasu   +2 more
doaj   +1 more source

Programming Actuation in 3D‐Printed Micro‐Architectures via Interfacial Adhesion Control

Advanced Materials Technologies, EarlyView.
A two‐phase meniscus‐guided 3D printing method directly fabricates microscale poly(3,4‐ethylenedioxythiophene) polystyrene sulfonate (PEDOT:PSS) and poly(vinyl alcohol) (PVA) bilayers with in situ programmable interfaces. Modulating the meniscus stretching speed switches the interface between separated and bonded states, which controls the mechanical ...
Xiao Huan, Juhyung Kim, Yujin Park, Shiqi Hu, Jihyuk Yang, Nan Huang, Feipeng Chen, Yu Liu, Sixi Cao, Zhuoran Wang, Ho Cheung Shum, Barbara Pui Chan, Dongwoon Shin, Ji Tae Kim   +13 more
wiley   +1 more source

Spark: modular spiking neural networks

Frontiers in Artificial Intelligence
Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy.
Mario Franco, Carlos Gershenson
doaj   +1 more source

On‐Chip Photonic Neural Network Architectures

Advanced Optical Materials, EarlyView.
This review presents a comprehensive overview of on‐chip photonic neural network architectures, covering key photonic building blocks, representative network types, and emerging applications. Recent advances, implementation challenges, and future directions are examined, highlighting the potential of integrated photonics to enable ultrafast, energy ...
Seokjin Hong, Berkay Neseli, Seungyeon Cho, Seungsoo Lee, Yeonjun Kim, Seungyoon Choi, Hyo‐Hoon Park, Hamza Kurt   +7 more
wiley   +1 more source

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch

Frontiers in Neuroinformatics
Spiking neural network simulations are a central tool in Computational Neuroscience, Artificial Intelligence, and Neuromorphic Engineering research. A broad range of simulators and software frameworks for such simulations exist with different target ...
Marius Vieth, Ali Rahimi, Ashena Gorgan Mohammadi, Jochen Triesch, Mohammad Ganjtabesh   +4 more
doaj   +1 more source