协同学习系统：概念、架构、算法

协同学习系统(I)：

概念、架构、算法

郭平

北京师范大学图形图像与模式识别实验室

整体大于部分之和 ----亚里士多德

摘要：借鉴大脑发展是“演化+选择”的达尔文过程，以及宇宙演化过程中温度与引力局部平衡等自组织与演化过程的思想，我们提出了一个称为“协同学习系统”的人工智能系统。该系统由两个或多个子系统（模型、智能体或虚拟体）组成，是一个开放的复杂巨系统。受自然智能（包括人类智能和生物智能）的启发，该系统通过合作/竞争协同学习实现给定环境下的智能信息处理与决策。自然界遵循的“物竞天择、适者生存”法则，在人工智能系统演化时应采用“人择”法则。因此，我们期望所提出的系统架构也可用于人-机协同、多自主体协同系统。期望在我们设计的准则下，该系统通过长时协同演化，最终实现通用人工智能。

关键词：人工智能系统；协同学习；自组织；协同演化；复杂网络结构。

Synergetic Learning Systems (I):

Concept, Architecture, and Algorithms

Ping Guo

Image Processing and Pattern Recognition Laboratory,

School of Systems Science, Beijing Normal University,Beijing 100875, China

The whole is greater than the sum of its parts — Aristotle

Abstract:Drawing on the idea that brain development is a Darwinian process of ``evolution + selection'', and the idea that current state is a local equilibrium state of many bodies with self-organization and evolution process driven by the temperature and gravity in our Universe, in this work, we describe an artificial intelligence system called ``Synergetic Learning System". The system is composed by two or more sub-systems (models, agents or virtual bodies), and it is an open complex giant system. Inspired by the natural intelligence (including human intelligence and biological intelligence), the system achieves intelligent information processing and decision-making in a given environment through cooperative/competitive synergetic learning. The intelligence is evolved from natural law of ``It is not the strongest of the species that survive, but the one most responsive to change'', while an artificial intelligence system should adopt the law of ``human selection'' in the evolution process. Therefore, we expect that the proposed system architecture can also be adapted in human -- machine synergy or multi-agent collaborative systems. It is also expected that under our design criteria, the proposed system will eventually achieve artificial general intelligence (AGI) through long term co-evolution.

Key words:Artificial Intelligence Systems, Synergetic Learning, Self-Organization, Synergetic Evolution, Complex Network Structure.

图1. 协同学习系统架构示意图。

备注：该摘要是投稿第三届系统科学大会的论文。http://iss.amss.cas.cn/cssc2019/