记录第一人称体验以构建新型基础模型
Recording First-person Experiences to Build a New Type of Foundation Model
AI总结:
本文提出通过可穿戴装置同步记录第一人称视听、GSR、面部表情与14通道EEG数据,构建能更真实复刻人类行为的新型基础模型。
摘要:
近年来,基础模型产生了巨大影响,在当前的人工智能热潮中,数十亿美元正被投入其中。更受欢迎的模型(例如 Chat-GPT)是在大量互联网数据上训练的。然而,越来越明显的是,这些数据可能很快就会耗尽,科技公司正在寻找新的数据来源,以训练下一代基础模型。强化学习、RAG、提示工程和认知建模常被用于微调和增强基础模型的行为。这些技术已被用于复刻人物,例如 Caryn Marjorie。这些聊天机器人并非基于人们对其环境的真实情绪和生理反应,因此,对于其所模仿的人物而言,它们充其量只是表层近似。为解决这些问题,我们开发了一套记录装置,可捕捉佩戴者所见所闻,以及其皮肤电导(GSR)、面部表情和大脑状态(14通道 EEG)。人工智能算法被用于处理这些数据,以形成关于环境和受试者内部状态的丰富图景。在此类数据上训练的基础模型,能够比迄今开发的人格模型更准确地复刻人类行为。这类模型具有许多潜在应用,包括推荐、个人助理、GAN 系统、约会和招聘。本文介绍了这项工作的一些背景,描述了该记录装置及其功能的初步测试。随后,本文提出如何利用该装置捕捉的数据创建一种新型基础模型,并概述了若干应用。数据收集和模型训练成本高昂,因此我们目前正致力于创办一家初创公司,以便为该项目的下一阶段筹集资金。
英文摘要:
Foundation models have had a big impact in recent years and billions of dollars are being invested in them in the current AI boom. The more popular ones, such as Chat-GPT, are trained on large amounts of Internet data. However, it is becoming apparent that this data is likely to be exhausted soon, and technology companies are looking for new sources of data to train the next generation of foundation models. Reinforcement learning, RAG, prompt engineering and cognitive modelling are often used to fine-tune and augment the behaviour of foundation models. These techniques have been used to replicate people, such as Caryn Marjorie. These chatbots are not based on people's actual emotional and physiological responses to their environment, so they are, at best, a surface-level approximation to the characters they are imitating. To address these issues, we have developed a recording rig that captures what the wearer is seeing and hearing as well as their skin conductance (GSR), facial expression and brain state (14 channel EEG). AI algorithms are used to process this data into a rich picture of the environment and internal states of the subject. Foundation models trained on this data could replicate human behaviour much more accurately than the personality models that have been developed so far. This type of model has many potential applications, including recommendation, personal assistance, GAN systems, dating and recruitment. This paper gives some background to this work and describes the recording rig and preliminary tests of its functionality. It then suggests how a new type of foundation model could be created from the data captured by the rig and outlines some applications. Data gathering and model training are expensive, so we are currently working on the launch of a start-up that could raise funds for the next stage of the project.
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。