Results 171 to 180 of about 435,912 (249)

Memory‐Reduced Convolutional Neural Network for Fast Phase Hologram Generation

open access: yesAdvanced Intelligent Systems, EarlyView.
This article reports a lightweight convolutional neural network framework using INT8 quantization to efficiently generate 3D computer‐generated holograms from a single 2D image. The quantized model reduces memory usage and computational cost, accelerates inference speed, and maintains high output quality, enabling real‐time holographic display on low ...
Chenliang Chang   +6 more
wiley   +1 more source

Machine Learning‐Based Standard Compact Model Binning Parameter Extraction Methodology for Integrated Circuit Design of Next‐Generation Semiconductor Devices

open access: yesAdvanced Intelligent Systems, EarlyView.
This study presents a neural network‐based methodology for Berkeley Short‐Channel IGFET Model–Common Multi‐Gate parameter extraction of gate‐all‐around field effect transistors, integrating binning adaptive sampling and transformer neural networks to efficiently capture current–voltage and capacitance–voltage characteristics.
Jaeweon Kang   +4 more
wiley   +1 more source

Quantum approximate multi-objective optimization. [PDF]

open access: yesNat Comput Sci
Kotil A   +6 more
europepmc   +1 more source

Hierarchical Language Models for Semantic Navigation and Manipulation in an Aerial‐Ground Robotic System

open access: yesAdvanced Intelligent Systems, EarlyView.
A hierarchical multimodal framework coupling a large language model for task decomposition and semantic mapping with a fine‐tuned vision‐language model for semantic perception, enhanced by GridMask, is presented. An aerial‐ground robot team exploits the semantic map for global and local planning.
Haokun Liu   +6 more
wiley   +1 more source

A Novel Contact‐Implicit Trajectory Optimization Framework for Quadruped Locomotion without Fixed Contact Sequences

open access: yesAdvanced Intelligent Systems, EarlyView.
Legged robots have advanced in environmental interaction through contact, but most works rely on fixed contact sequences. This work presents a new method based on an indirect optimization method for legged robots to automatically generate contact sequences for complex movements.
Yaowei Chen, Jie Zhang, Ming Lyu
wiley   +1 more source

Large‐Scale and Highly Reliable Hopfield Neural Networks Using Vertical NAND Flash Memory for the In‐Memory Associative Computing

open access: yesAdvanced Intelligent Systems, EarlyView.
Large‐scale Hopfield neural networks (HNNs) for associative computing are implemented using vertical NAND (VNAND) flash memory. The proposed VNAND HNN with the asynchronous update scenario achieve robust image restoration performance despite fabrication variations, while significantly reducing chip area (≈117× smaller than resistive random‐access ...
Jin Ho Chang   +4 more
wiley   +1 more source

Home - About - Disclaimer - Privacy