Search scope:
排序: Display mode:
Frontiers of Mechanical Engineering 2022, Volume 17, Issue 3, doi: 10.1007/s11465-022-0698-y
Keywords: minimally invasive surgery hand−eye calibration intuitive control surgical robot dual quaternion
Soundscape of classical Chinese garden
YUAN Xiaomei, WU Shuoxian
Frontiers of Structural and Civil Engineering 2008, Volume 2, Issue 2, Pages 172-178 doi: 10.1007/s11709-008-0026-6
Keywords: observation classical phenomena intuitive soundscape
An intuitive general rank-based correlation coefficient Research Articles
Divya PANDOVE, Shivani GOEL, Rinkle RANI
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 6, Pages 699-711 doi: 10.1631/FITEE.1601549
Keywords: General rank-based correlation coefficient Multivariate analysis Predictive metric Spearman’s rank correlation coefficient
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense Feature Article
Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu
Engineering 2020, Volume 6, Issue 3, Pages 310-345 doi: 10.1016/j.eng.2020.01.011
Recent progress in deep learning is essentially based on a “big data for small tasks” paradigm, under which massive amounts of data are used to train a classifier for a single narrow task. In this paper, we call for a shift that flips this paradigm upside down. Specifically, we propose a “small data for big tasks” paradigm, wherein a single artificial intelligence (AI) system is challenged to develop “common sense,” enabling it to solve a wide range of tasks with little training data. We illustrate the potential power of this new paradigm by reviewing models of common sense that synthesize recent breakthroughs in both machine and human vision. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense. When taken as a unified concept, FPICU is concerned with the questions of “why” and “how,” beyond the dominant “what” and “where” framework for understanding vision. They are invisible in terms of pixels but nevertheless drive the creation, maintenance, and development of visual scenes. We therefore coin them the “dark matter” of vision. Just as our universe cannot be understood by merely studying observable matter, we argue that vision cannot be understood without studying FPICU. We demonstrate the power of this perspective to develop cognitive AI systems with humanlike common sense by showing how to observe and apply FPICU with little training data to solve a wide range of challenging tasks, including tool use, planning, utility inference, and social learning. In summary, we argue that the next generation of AI must embrace “dark” humanlike common sense for solving novel tasks.
Keywords: Computer vision Artificial intelligence Causality Intuitive physics Functionality Perceived intent
Yun Gao,Xiang Gao,Xiaohua Zhang
Engineering 2017, Volume 3, Issue 2, Pages 272-278 doi: 10.1016/J.ENG.2017.01.022
The Paris Agreement proposed to keep the increase in global average temperature to well below 2 °C above pre-industrial levels and to pursue efforts to limit the temperature increase to 1.5 °C above pre-industrial levels. It was thus the first international treaty to endow the 2 °C global temperature target with legal effect. The qualitative expression of the ultimate objective in Article 2 of the United Nations Framework Convention on Climate Change (UNFCCC) has now evolved into the numerical temperature rise target in Article 2 of the Paris Agreement. Starting with the Second Assessment Report (SAR) of the Intergovernmental Panel on Climate Change (IPCC), an important task for subsequent assessments has been to provide scientific information to help determine the quantified long-term goal for UNFCCC negotiation. However, due to involvement in the value judgment within the scope of non-scientific assessment, the IPCC has never scientifically affirmed the unacceptable extent of global temperature rise. The setting of the long-term goal for addressing climate change has been a long process, and the 2 °C global temperature target is the political consensus on the basis of scientific assessment. This article analyzes the evolution of the long-term global goal for addressing climate change and its impact on scientific assessment, negotiation processes, and global low-carbon development, from aspects of the origin of the target, the series of assessments carried out by the IPCC focusing on Article 2 of the UNFCCC, and the promotion of the global temperature goal at the political level.
Keywords: Change United Nations Framework Convention on Climate Change Long-term goal Critical vulnerability Intuitive
Title Author Date Type Operation
Development of a novel hand−eye calibration for intuitive control of minimally invasive surgical robot
Journal Article
An intuitive general rank-based correlation coefficient
Divya PANDOVE, Shivani GOEL, Rinkle RANI
Journal Article
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu
Journal Article