arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.04571cs.AIcs.CYq-bio.NC
收藏

将人工智能与人工意识相分离

Dissociating Artificial Intelligence from Artificial Consciousness

University of Wisconsin（威斯康星大学）；Brock University（布洛克大学）；Allen Institute（艾伦研究所）

Graham Findlay, William Marshall, Larissa Albantakis, Isaac David, William GP Mayner, Christof Koch, Giulio Tononi

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文基于整合信息理论（IIT）证明，两个功能等价的系统在现象上可能不等价，数字计算机可模拟人类行为而不复制其体验，从而将人工智能与人工意识分离。

摘要：

机器学习和计算能力的发展表明，通用人工智能已触手可及。这引发了关于人工意识的问题：如果一台计算机在功能上与人类等价，能够做我们所做的一切，它是否会像我们有意识时那样体验视觉、声音和思想？要以有原则的方式回答这个问题，只能建立在基于现象学的意识理论之上，该理论需阐明任何系统（无论是演化而来的还是工程设计的）支持主观体验的充分必要条件。在此，我们采用整合信息理论（IIT），该理论提供了有原则的工具来确定一个系统是否有意识、意识的程度以及其体验的内容。我们考虑了由简单布尔单元组成的系统对，其中一个系统——一台基本的存储程序计算机——以完全的功能等价性模拟另一个系统。通过应用IIT的原则，我们证明：（i）两个系统可以在功能上等价但在现象上不等价；（ii）这一结论不依赖于被模拟系统的功能。我们进一步证明，根据IIT，数字计算机有可能通过模拟我们大脑中的神经元来模拟我们的行为，却无法复制我们的体验。这与计算功能主义形成了鲜明对比，后者认为执行正确类型的计算是产生意识的必要充分条件。

英文摘要：

Developments in machine learning and computing power suggest that artificial general intelligence is within reach. This raises the question of artificial consciousness: if a computer were to be functionally equivalent to a human, being able to do all we do, would it experience sights, sounds, and thoughts, as we do when we are conscious? Answering this question in a principled manner can only be done on the basis of a theory of consciousness that is grounded in phenomenology and that states the necessary and sufficient conditions for any system, evolved or engineered, to support subjective experience. Here we employ Integrated Information Theory (IIT), which provides principled tools to determine whether a system is conscious, to what degree, and the content of its experience. We consider pairs of systems constituted of simple Boolean units, one of which -- a basic stored-program computer -- simulates the other with full functional equivalence. By applying the principles of IIT, we demonstrate that (i) two systems can be functionally equivalent without being phenomenally equivalent, and (ii) that this conclusion is not dependent on the simulated system's function. We further demonstrate that, according to IIT, it is possible for a digital computer to simulate our behavior, possibly even by simulating the neurons in our brain, without replicating our experience. This contrasts sharply with computational functionalism, the thesis that performing computations of the right kind is necessary and sufficient for consciousness.

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。

↑