arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.04660cs.AI
收藏

为什么人工智能需要任务理论--以及它可能是什么样子

Why Artificial Intelligence Needs a Task Theory --- And What It Might Look Like

Icelandic Institute for Intelligent Machines（冰岛智能机器研究所）；Reykjavik University（雷克雅未克大学）；The Swiss AI Lab IDSIA（瑞士人工智能实验室IDSIA）

Kristinn R. Thórisson, Jordi Bieger, Thröstur Thorarensen, Jóna S. Sigurðardóttir, Bas R. Steunebrink

备注：
accepted to the Ninth Conference on Artificial General Intelligence (AGI-16)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

“任务”的概念是人工智能（AI）的核心：任务用于训练和评估人工智能系统，这些系统是按照内置的序构建的，用于执行和自动化我们认为有用的任务。在其他工程领域，理论基础允许通过对具有已知作用和重要性的众所周知的参数进行有条理的操作来对设计进行彻底的评估;这允许航空工程师，例如，系统地评估风速对飞机性能和稳定性的影响。在人工智能中不存在允许这种有条不紊的操作的框架：当前使用的少数任务的性能结果（参见。棋盘游戏，问答）不能很容易地比较，无论相似或不同。这个问题在人工智能系统方面更加尖锐，它必须处理无法预料的任务，这些任务的具体细节无法事先知道。任务理论将能够在类的层次上处理任务，绕过它们的细节，提供任务、环境及其参数的适当形式化和分类，从而产生更严格的测量、比较和评估智能行为的方法。即使在这个方向上进行适度的改进，也会超过当前机器学习和人工智能评估的特设性质。在这里，我们讨论了任务理论的主要论点，并提出了一个大纲，它可能看起来像物理任务。

英文摘要：

The concept of "task" is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical foundations allow thorough evaluation of designs by methodical manipulation of well understood parameters with a known role and importance; this allows an aeronautics engineer, for instance, to systematically assess the effects of wind speed on an airplane's performance and stability. No framework exists in AI that allows this kind of methodical manipulation: Performance results on the few tasks in current use (cf. board games, question-answering) cannot be easily compared, however similar or different. The issue is even more acute with respect to artificial *general* intelligence systems, which must handle unanticipated tasks whose specifics cannot be known beforehand. A *task theory* would enable addressing tasks at the *class* level, bypassing their specifics, providing the appropriate formalization and classification of tasks, environments, and their parameters, resulting in more rigorous ways of measuring, comparing, and evaluating intelligent behavior. Even modest improvements in this direction would surpass the current ad-hoc nature of machine learning and AI evaluation. Here we discuss the main elements of the argument for a task theory and present an outline of what it might look like for physical tasks.

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。

↑