DeepMind公司人工智能研发组织模式分析  

Analysis of DeepMind’s Artificial Intelligence R&D Organization Mode

作　　者：刘鑫怡 徐峰[1] 张东[1] Liu Xinyi;Xu Feng;Zhang Dong(Artificial Intelligence Development Research Center,Institute of Scientific and Technical Information of China,Beijing 100038,China)

机构地区：[1]中国科学技术信息研究所人工智能发展研究中心,北京100038

出　　处：《科技管理研究》2022年第14期8-13,共6页Science and Technology Management Research

基　　金：科技创新2030——“新一代人工智能”重大项目“重点领域人工智能伦理风险及对策研究”(2020AAA0105301)。

摘　　要：国际上大型科技公司正在以收购公司、设立分支机构等方式加快建设人工智能实验室,在人工智能研发方面抢占先机。人工智能实验室DeepMind被谷歌母公司Alphabet收购以来,以实现通用人工智能为核心目标,构建矩阵型、网络开放式的研发组织结构,通过灵活的项目运作模式、跨学科的工作方式、长期的资本投入和高水平的人才培养体系,在生物、医疗、能源等多个领域取得重大突破。其研发组织模式的做法和经验对中国加强人工智能前瞻性研发部署、企业设立人工智能实验室、人工智能产学研用深度融合和开放合作等方面提供一定的启发和借鉴。Large technology companies are accelerating the construction of artificial intelligence laboratories by acquiring companies and setting up branches to seize opportunities in artificial intelligence(AI) R&D. Since its acquisition by Google’s parent company Alphabet, DeepMind has built a matrix-type, open-network R&D organizational structure with the core goal of achieving general AI. Through flexible project operation mode,interdisciplinary working methods, long-term capital investment and high-level talent training system, DeepMind has made a major AI breakthrough in many fields such as biology, medical care, and energy. It’s unique R&D organization mode provide certain inspiration and experience for China to strengthen the deployment of forward-looking R&D of AI, encourage enterprises to set up AI laboratories, deepen in-depth integration of industry, academia, research and application, and strengthen open cooperation in AI.

关 键 词：人工智能 人工智能实验室 研发组织模式 跨学科 矩阵结构 

分 类 号：G311[文化科学]