arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.03595cs.AIcs.DCcs.MA
收藏

Federated AI让团队一起想象:GANs的联邦学习

Federated AI lets a team imagine together: Federated Learning of GANs

Rajagopal. A, Nirmala. V

摘要:

共同设想一个新的富有想象力的想法是人类普遍的需求。作为一个团队一起想象往往会带来突破性的想法,但协作工作也可能具有挑战性,特别是当团队成员被时间和空间分开时。如果有一个人工智能可以帮助团队协同设想新的想法呢?有没有可能开发出这样一种人工智能的工作模型?本文旨在设计这样一种智能。本文提出了一种方法来设计一个创造性的和协作的智能,采用一种形式的分布式机器学习方法,称为联邦学习以及融合生成对抗网络,GAN。这种协作式的创造性人工智能提出了一种新的人工智能模式,它让两个或两个以上的团队走到一起,想象和设想与团队所有成员的利益协同的想法。简而言之,本文探讨了一种新型AI范式的设计,称为Federated AI Imagination,它可以让地理上分布的团队协同想象。

英文摘要:

Envisioning a new imaginative idea together is a popular human need. Imagining together as a team can often lead to breakthrough ideas, but the collaboration effort can also be challenging, especially when the team members are separated by time and space. What if there is a AI that can assist the team to collaboratively envision new ideas?. Is it possible to develop a working model of such an AI? This paper aims to design such an intelligence. This paper proposes a approach to design a creative and collaborative intelligence by employing a form of distributed machine learning approach called Federated Learning along with fusion on Generative Adversarial Networks, GAN. This collaborative creative AI presents a new paradigm in AI, one that lets a team of two or more to come together to imagine and envision ideas that synergies well with interests of all members of the team. In short, this paper explores the design of a novel type of AI paradigm, called Federated AI Imagination, one that lets geographically distributed teams to collaboratively imagine.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑