Specialized intelligent systems can be found everywhere: finger print, handwriting, speech, and face recognition, spam filtering, chess and other game programs, robots, et al. This decade the first presumably complete mathematical theory of artificial intelligence based on universal induction-prediction-decision-action has been proposed. This information-theoretic approach solidifies the foundations of inductive inference and artificial intelligence. Getting the foundations right usually marks a significant progress and maturing of a field. The theory provides a gold standard and guidance for researchers working on intelligent algorithms. The roots of universal induction have been laid exactly half-a-century ago and the roots of universal intelligence exactly one decade ago. So it is timely to take stock of what has been achieved and what remains to be done. Since there are already good recent surveys, I describe the state-of-the-art only in passing and refer the reader to the literature. This article concentrates on the open problems in universal induction and its extension to universal intelligence.
Universal Induction with Varying Sets of Combinators
AIDEUS;National Research University of Information Technology, Mechanics and Optics(国立信息技术、机械与光学研究大学);Aix Marseille Université(艾克斯-马赛大学);CNRS(法国国家科学研究中心)
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
决策理论正式解决了不确定世界中理性主体的问题,如果真实的环境概率分布是已知的。Solomonoff的泛归纳理论形式化地解决了未知分布的序列预测问题。我们统一了这两种理论,并给出了强有力的论据,由此产生的通用AIXI模型在任何可计算的环境中表现最佳。AIXI模型的主要缺点是它是不可计算的。为了克服这个问题,我们构造了一个改进的算法AIXI^tl,它仍然优于任何其他时间t和空间l有界代理。AIXI^tl的计算时间为t x 2^l的数量级。
Universal Algorithmic Intelligence: A mathematical top->down approach
序贯决策理论正式解决了不确定世界中的理性主体问题,如果真实的环境先验概率分布是已知的。Solomonoff的泛归纳理论形式化地解决了未知先验分布的序列预测问题。我们将这两种思想结合起来,得到一个无参数的通用人工智能理论。我们给出了强有力的论据,由此产生的AIXI模型是最智能的无偏代理可能。我们概述了AIXI模型如何正式解决一些问题类,包括序列预测,战略游戏,功能最小化,强化和监督学习。AIXI模型的主要缺点是它是不可计算的。为了克服这个问题,我们构造了一个修改后的算法AIXITl,它仍然有效地比任何其他时间t和长度l有界代理更智能。AIXITl的计算时间是t x 2^l的数量级。讨论了智能顺序关系的形式化定义、视界问题以及AIXI理论与其他人工智能方法的关系。
Assessing Adaptive World Models in Machines with Novel Games
MIT(麻省理工学院);Harvard University(哈佛大学);University of Cambridge(剑桥大学);Basis Research Institute(基础研究机构);Princeton University(普林斯顿大学);ARC Prize Foundation(ARC奖基金会);University of British Columbia(不列颠哥伦比亚大学)
本文提出用具有持续新颖性的新颖游戏构建基准,以评估 AI 智能体通过交互快速归纳世界模型并实现类人适应与泛化的能力。
Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey
Saw Swee Hock School of Public Health, National University of Singapore(新加坡国立大学公共健康学院);School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院)
Universal Empathy and Ethical Bias for Artificial General Intelligence
AIDEUS;National Research University of Information Technology, Mechanics and Optics(国立信息技术、机械与光学大学);Aix Marseille Université(艾克斯-马赛大学);CNRS(法国国家科学研究中心)
The ethics of artificial intelligence in the life sciences: Universality, cultural diversity and an architecture of care
Institut Pasteur(巴斯德研究所);Collège de France(法兰西公学院);Universitat Pompeu Fabra(庞培法布拉大学);Institució Catalana de la Recerca i Estudis Avançats (ICREA)(加泰罗尼亚研究与高等研究院(ICREA));University of Oxford(牛津大学);Aarhus University(奥胡斯大学)
Can Complexity and Uncomputability Explain Intelligence? SuperARC: A Test for Artificial Super Intelligence Based on Recursive Compression
Oxford Immune Algorithmics(牛津免疫算法公司);Oxford University Innovation(牛津大学创新中心);London Institute for Healthcare Engineering(伦敦医疗工程研究所);Algorithmic Dynamics Lab(算法动力实验室);Center of Molecular Medicine, Karolinska Institute(卡罗林斯卡研究所分子医学中心);King’s College London(伦敦大学国王学院);Centre for Logic, Epistemology and the History of Science, University of Campinas (UNICAMP)(逻辑、知识论和科学史研究中心,坎皮纳斯大学);DEXL, National Laboratory for Scientific Computing (LNCC)(DEXL,国家科学计算实验室);King’s Institute for Artificial Intelligence, King’s College London(伦敦大学国王学院人工智能研究所)
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
Google(谷歌);Mila - Quebec AI Institute(Mila-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);CIFAR(加拿大高等研究院);ETH Zürich(苏黎世联邦理工学院);Google DeepMind(谷歌DeepMind);Santa Fe Institute(圣塔菲研究所)
AI Pangaea: Unifying Intelligence Islands for Adapting Myriad Tasks
Huawei(华为);National Engineering and Research Center for Software Engineering, Peking University(软件工程国家工程与研究中心,北京大学);Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University(电子工程系,北京信息科学与技术国家研究中心,清华大学);State Key Laboratory of General AI, School of Intelligence Science and Technology, Peking University(通用人工智能国家重点实验室,智能科学与技术学院,北京大学)
本文提出 AI 超级大陆 Pangaea,通过统一数据格式并在 296 个多模态数据集上预训练,统一“智能孤岛”,在 45 个通用任务和 15 个科学任务上实现显著泛化,并揭示了跨模态知识积累的规模效应,为通用人工智能提供新方向。
First Draft on the xInf Model for Universal Physical Computation and Reverse Engineering of Natural Intelligence
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences(中国科学院苏州生物医学工程技术研究所);Technical University Munich(慕尼黑工业大学);Third Military Medical University(第三军医大学);Beijing AboroTech Co., Ltd.(北京AboroTech有限公司);Chongqing U-LaborTech Co., Ltd.(重庆U-LaborTech有限公司)
Computer sciences and synthesis: retrospective and perspective
Scientific Research Institute of System Analysis of Russian Academy of Sciences(俄罗斯科学院系统分析科学研究所);Lesya Ukrayinka Volyn National University(莱斯娅·乌克兰卡沃林国立大学)