|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Dark,Beyond Deep:A Paradigm Shift to Cognitive AI with Humanlike Common Sense显示文摘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. | 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 | 2020 | Engineering2020,6,3: | 3 |
| 2 | Analysis of variance techniques for unbalanced data显示文摘 | Edmond Marks | 1974 | Review of educational Research1974,44,3: | 1 |
| 3 | 吸入麻醉药在大鼠最小肺泡有效浓度上无协同作用显示文摘背景本研究假设对特定受体或通道具有不同作用强度[一种在最小肺泡麻醉药浓度(MAC)时作用弱,另一种则作用较强]的两个吸入麻醉药联合使用时可产生协同作用.这种非单纯相加的相互作用方式将支持麻醉药是通过多位点作用而产生麻醉效应的论点。方法根据药物作用强度差别(一个作用弱,一个作用强),我们研究了11组相加为1MAC的麻醉药物对某特定受体或通道的作用.此处“作用强度差别”是指两种麻醉药在体外对特定受体或通道的增强或阻断作用,按MAC计算,作用较强者至少是较弱者的两倍(或更多)。这些特定受体包括:TREK-1和TASK-3钾通道;γ-氨基丁酸A(GABAA)、甘氡酸、N-甲基-D-天门冬氡酸和乙酰胆碱受体。我们还研究了环丙烷-苯酚组合,因为N-甲基-D-天门冬氨酸受体阻滞剂MK-801对这两种药物MAC的影响明显不同。此外,纳入研究的还有4对包含氧化亚氯的组合,因为有报道氧化亚氮与异氟烷联合应用可产生亚相加作用(拮抗作用)。结果除氧化亚氮和异氟烷组合产生了拮抗作用之外,其余所有组合的作用强度均在所预计两者之和10%的范围以内.结论本研究结果支持“吸入麻醉药是作用于单一位点而抑制伤害刺激所致体动反应”的观点。 | Edmond I Eger II Michael Tang Mark Liao Michael J. Laster Ken Solt Pamela Flood Andrew lenkins Douglas Raines Jan F. Hendrickx Steven L. Shafer Tanifuji Yasumasa James M. Sonner 杨静(译) 米卫东(校) | 2010 | 麻醉与镇痛2010,,1: | 0 |
| 4 | 国际需求促进可编程电源的发展显示文摘严格的全球性标准导致产生更高效、更可靠。 | Mark Edmonds | 2000 | 今日电子2000,,9: | 0 |
| 5 | Daily heart rate variability of Paralympic gold medallist swimmers: A 17-week investigation显示文摘背景:心率变异分析(HRV)是测量高水平运动员周期训练负荷安排和减量训练过程中心脏自主神经系统波动的一种简单、无创的测量方法。本研究包括3个案例分析,目的是检测残奥会游泳冠军日常心脏自主神经波动的变化。方法:在残奥会之前的17周每天监测3名残奥会游泳冠军的静息HRV。在特定的时间和频率区域测试,并伴HRV非线性指标计算进行分析。所有HRV数据用每日值进行单独分析,用周平均值进行分析以及静息时相和训练时相均值进行分析。结果:在整个监测阶段,3名运动员(截肢运动员)所有的HRV参数均存在显著性差异。结论:在运动员监测过程中,尽管长期改变非常微小,游泳分类和残疾类型都能明显影响HRV。关于影响残疾运动员对训练、旅行和其他外界因素的个体反应进一步理解,可能会提高对增强运动表现运动负荷的管理和监控。 | Rohan Edmonds Anthony Leicht Mark McKean Brendan Burkett | 2015 | Journal of Sport and Health Science2015,4,4: | 0 |
| 6 | 每人支付5欧元!这是威尼斯的入城费还是逐客令?显示文摘意大利时间2023年11月27日,威尼斯市长宣布,从2024年4月起,游客进入威尼斯将不再免费。市长说:“如果您是公民,您将始终拥有大门的“钥匙”;如果您是客人,您将在作为客人期间拥有它。(威尼斯)有了入城费,就可以利用财务杠杆来劝阻那些没有预订进入城市的人。” | 蒋雨宁 Edmond Yuen(图) 张鹏(图) Luca Bravo(图) canmandawe(图) Tao Qi(图) Danil(图) Markus(图) Nikhg(图) Natalia(图) Mark(图) Alena(图) scaliger(图) | 2024 | 环球人文地理2024,,1: | 0 |