arXiv 1911.015472019-11-25cs.AI

论智力的测量

On the Measure of Intelligence

Google, Inc.（谷歌公司）

François Chollet

摘要：

为了朝着更智能、更人性化的人工系统迈进，我们需要遵循一个适当的反馈信号：我们需要能够以一种能够在两个系统之间进行比较以及与人类进行比较的方式来定义和评估智能。在过去的一百年里，在心理学和人工智能领域都有大量的尝试来定义和测量智力。我们总结和批判性地评估这些定义和评估方法，同时使明显的两个历史概念的智能，隐含地指导他们。我们注意到，在实践中，当代人工智能社区仍然倾向于通过比较人工智能和人类在特定任务（如棋盘游戏和视频游戏）中表现出的技能来对智能进行基准测试。我们认为，仅仅测量任何给定任务的技能都不足以测量智力，因为技能受到先验知识和经验的严重影响：无限的先验知识或无限的训练数据允许实验者为系统“购买”任意水平的技能，以掩盖系统自身的泛化能力。然后，我们阐明了一个新的正式定义的智能的基础上，数学信息论，描述智能的技能获取效率和突出的范围，概括困难，先验和经验的概念。使用这个定义，我们提出了一套通用AI基准应该是什么样子的指导方针。最后，我们提出了一个基准密切遵循这些准则，抽象和推理语料库（ARC），建立在一组明确的先验设计，尽可能接近先天人类先验。我们认为，ARC可以用来衡量一种类似人类的一般流体智力，并且它可以在AI系统和人类之间进行公平的一般智力比较。

英文摘要：

To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.

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。

摘要：

英文摘要：

相关论文