Designing Ecosystems of Intelligence from First Principles-猫眼课题宝

DOI：

10.1177/26339137231222481

发表时间：

2022-12

期刊：

Collective Intelligence

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Karl J. Friston;M. Ramstead;Alex B. Kiefer;Alexander Tschantz;C. Buckley;Mahault Albarracin;R. J. Pitliya;Conor Heins;Brennan Klein;Beren Millidge;D. A. R. Sakthivadivel;T. S. C. Smithe;Magnus T. Koudahl;Safae Essafi Tremblay;C.G. Petersen;K. Fung;Jason G. Fox;S. Swanson;D. Mapes;Gabriel Ren'e

这篇白色论文阐述了未来十年（及以后）人工智能领域的研究和发展愿景。它的结局是一个自然和合成意义制造的网络物理生态系统，其中人类是不可或缺的参与者，我们称之为“共享智能”。这一愿景建立在主动推理的基础上，主动推理是一种自适应行为的表述，可以被解读为智能的物理学，它继承自组织的物理学。在这种情况下，我们将智力理解为一种为一个人的感觉世界的生成模型积累证据的能力，也被称为自我证明。形式上，这对应于最大化（贝叶斯）模型证据，通过在几个尺度上的信念更新，即推理，学习和模型选择。在操作上，这种自我证明可以通过因子图上的（变化的）消息传递或信念传播来实现。至关重要的是，主动推理突出了智能系统的存在必要性，即好奇心或解决不确定性。同样的命令在代理集合中支持信念共享，其中某些方面（即，每个主体的生成世界模型的所有要素（例如，因素）提供了共同的基础或参考框架。主动推理在这种信仰共享的生态中扮演着基础性的角色，它导致了对集体智慧的正式描述，而集体智慧建立在共同的叙述和目标之上。我们还考虑了必须开发的通信协议的种类，以实现这样的智能生态系统，并激励共享的超空间建模语言和交易协议的发展，作为迈向这样的生态系统的第一步和关键一步。

This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosystem of natural and synthetic sense-making, in which humans are integral participants—what we call “shared intelligence.” This vision is premised on active inference, a formulation of adaptive behavior that can be read as a physics of intelligence, and which inherits from the physics of self-organization. In this context, we understand intelligence as the capacity to accumulate evidence for a generative model of one’s sensed world—also known as self-evidencing. Formally, this corresponds to maximizing (Bayesian) model evidence, via belief updating over several scales, that is, inference, learning, and model selection. Operationally, this self-evidencing can be realized via (variational) message passing or belief propagation on a factor graph. Crucially, active inference foregrounds an existential imperative of intelligent systems; namely, curiosity or the resolution of uncertainty. This same imperative underwrites belief sharing in ensembles of agents, in which certain aspects (i.e., factors) of each agent’s generative world model provide a common ground or frame of reference. Active inference plays a foundational role in this ecology of belief sharing—leading to a formal account of collective intelligence that rests on shared narratives and goals. We also consider the kinds of communication protocols that must be developed to enable such an ecosystem of intelligences and motivate the development of a shared hyper-spatial modeling language and transaction protocol, as a first—and key—step towards such an ecology.

Designing Ecosystems of Intelligence from First Principles

文献摘要

相似文献