arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03569cs.HCcs.AI
收藏

人类参与机器创造力的循环

Human in the Loop for Machine Creativity

Institute of Informatics, University of Warsaw(华沙大学信息学研究所)

Neo Christopher Chung

摘要:

人工智能(AI)越来越多地用于合成视觉,文本和音频。这些基于人工智能的作品,通常来自神经网络,正在进入主流市场,如数字绘画,歌曲,书籍等。我们将现有和未来的人在回路(HITL)方法概念化,用于创造性应用,并开发更具表现力,细致入微和多模态的模型。特别是,我们作为策展人和合作者的专业知识如何以交互的方式编码在AI模型中?我们研究和推测对模型,界面和机器创造力的长期影响。我们对人工智能艺术的选择、创作和解释本质上包含了我们的情感反应、文化和背景。因此,所提出的HITL可以帮助算法学习更难以编码或量化的创造性过程。我们设想多模态HITL过程,其中文本,视觉,声音和其他信息耦合在一起,对人类和环境进行自动分析。总的来说,这些HITL方法将增加人类与人工智能之间的互动,从而帮助未来的人工智能系统更好地理解我们自己的创造和情感过程。

英文摘要:

Artificial intelligence (AI) is increasingly utilized in synthesizing visuals, texts, and audio. These AI-based works, often derived from neural networks, are entering the mainstream market, as digital paintings, songs, books, and others. We conceptualize both existing and future human-in-the-loop (HITL) approaches for creative applications and to develop more expressive, nuanced, and multimodal models. Particularly, how can our expertise as curators and collaborators be encoded in AI models in an interactive manner? We examine and speculate on long term implications for models, interfaces, and machine creativity. Our selection, creation, and interpretation of AI art inherently contain our emotional responses, cultures, and contexts. Therefore, the proposed HITL may help algorithms to learn creative processes that are much harder to codify or quantify. We envision multimodal HITL processes, where texts, visuals, sounds, and other information are coupled together, with automated analysis of humans and environments. Overall, these HITL approaches will increase interaction between human and AI, and thus help the future AI systems to better understand our own creative and emotional processes.

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。

↑