Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 7

Year

2023 2

2021 1

2018 1

2007 1

2006 1

Keywords

Alignment correction 1

Artificial general intelligence 1

Artificial intelligence benchmark 1

Artificial intelligence evaluation 1

Association rules 1

Beta-mixture model 1

Causality 1

Cross-domain 1

Cross-modal retrieval 1

Domain alignment 1

Embodied artificial intelligence 1

Optimization steps 1

Robust learning 1

Semantic discrimination 1

Sentiment classification 1

Turing test 1

Unsupervised domain adaptation 1

Value alignment 1

adaptive tungsten 1

adjustment 1

open ︾

Search scope:

排序： Display mode:

A nano-scale alignment method for imprint lithography

WANG Li, LU Bing-heng, DING Yu-cheng, QIU Zhi-hui, LIU Hong-zhong

Frontiers of Mechanical Engineering 2006, Volume 1, Issue 2, Pages 157-161 doi: 10.1007/s11465-006-0014-2

Abstract: A novel nano-scale alignment technique based on moiré signal for room-temperature imprint lithographyprojected onto two photo-detector arrays, then the detected moiré signals are used to estimate the alignmentcomplex differential moiré signal is sensitive to relative displacement of the mold and wafer, and the alignmentThey can meet the requirements of alignment accuracy for submicron imprint lithography.

Keywords： submicron alignment accuracy nano-scale alignment quadruple room-temperature

HTML PDF Collect

Coordinated shift control of nonsynchronizer transmission for electric vehicles based on dynamic tooth alignment

Frontiers of Mechanical Engineering 2021, Volume 16, Issue 4, Pages 887-900 doi: 10.1007/s11465-021-0653-3

Abstract: of gear shifting, this paper proposes a coordinated shift control method based on the dynamic tooth alignment

Keywords： automated mechanical transmission (NSAMT) planetary gear coordinated shift control dynamic tooth alignment

HTML PDF Collect

Robust cross-modal retrieval with alignment refurbishment Research Article

Jinyi GUO, Jieyu DING,jinyi_g@njust.edu.cn,djy@qdu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 10, Pages 1403-1415 doi: 10.1631/FITEE.2200514

Abstract: tries to achieve mutual retrieval between modalities by establishing consistent alignment for differentcross-modal pairs, which are semantically matched but costly, compared with easily available data with noise alignmentTherefore, we propose a robust with alignment refurbishment (RCAR), which significantly reduces theand noise alignments and refurbishes the label according to the posterior probability of the noise-alignmentIn addition, we define partial and complete noises in the noise-alignment paradigm.

Keywords： Cross-modal retrieval Robust learning Alignment correction Beta-mixture model

HTML PDF Collect

Laser vision sensing based on adaptive welding for aluminum alloy

CHEN Zhixiang, SONG Yonglun, ZHANG Jun, ZHANG Wanchun, JIANG Li, XIA Xuxin

Frontiers of Mechanical Engineering 2007, Volume 2, Issue 2, Pages 218-223 doi: 10.1007/s11465-007-0038-2

Abstract: They were also applied for automatic seam tracking, such as automatic torch transverse alignment and

Keywords： adjustment adaptive tungsten transverse alignment large-scale aluminum geometry

HTML PDF Collect

Dynamic parameterized learning for unsupervised domain adaptation Research Article

Runhua JIANG, Yahong HAN

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1616-1632 doi: 10.1631/FITEE.2200631

Abstract: First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to

Keywords： Unsupervised domain adaptation Optimization steps Domain alignment Semantic discrimination

HTML PDF Collect

Words alignment based on association rules for cross-domain sentiment classification None

Xi-bin JIA, Ya JIN, Ning LI, Xing SU, Barry CARDIFF, Bir BHANU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 2, Pages 260-272 doi: 10.1631/FITEE.1601679

Abstract: In this paper, we propose a novel approach called words alignment based on association rules (WAAR) for

Keywords： Sentiment classification Cross-domain Association rules

HTML PDF Collect

The Tong Test: Evaluating Artificial General Intelligence Through Dynamic Embodied Physical and Social Interactions

Yujia Peng,Jiaheng Han,Zhenliang Zhang,Lifeng Fan,Tengyu Liu,Siyuan Qi,Xue Feng,Yuxi Ma,Yizhou Wang,Song-Chun Zhu,

Engineering doi: 10.1016/j.eng.2023.07.006

Abstract: The release of the generative pre-trained transformer (GPT) series has brought artificial general intelligence (AGI) to the forefront of the artificial intelligence (AI) field once again. However, the questions of how to define and evaluate AGI remain unclear. This perspective article proposes that the evaluation of AGI should be rooted in dynamic embodied physical and social interactions (DEPSI). More specifically, we propose five critical characteristics to be considered as AGI benchmarks and suggest the Tong test as an AGI evaluation system. The Tong test describes a value- and ability-oriented testing system that delineates five levels of AGI milestones through a virtual environment with DEPSI, allowing for infinite task generation. We contrast the Tong test with classical AI testing systems in terms of various aspects and propose a systematic evaluation system to promote standardized, quantitative, and objective benchmarks and evaluation of AGI.

Keywords： Artificial intelligence benchmark Artificial intelligence evaluation Embodied artificial intelligence Value alignment