◎刘宜庭

AI has gotten pretty good at completing specific tasks, but it’s still a long way from having general intelligence. One of the key elements of general intelligence is abstract reasoning — the ability to think beyond the "here and now" to see more nuanced patterns and relationships and to engage in complex thought.

人工智慧在完成特定任务上已经成果斐然，但在拥有一般智力上还有很长的一段路要走。「一般智力」的关键要素之一是「抽象推理」；这种能力可以超越「此时此地」进行思考，领会到更多具有细微差别的模式及关联，并参与复杂思维。

On July 11th, researchers at DeepMind — a Google subsidiary focused on artificial intelligence — published a paper detailing their attempt to measure various AIs’ abstract reasoning capabilities.

7月11日，聚焦人工智慧的Google子公司DeepMind研究团队发表一篇论文，详述他们如何尝试评估各种人工智慧的抽象推理能力。

In humans, we measure abstract reasoning using fairly straightforward visual IQ tests. One popular test, called Raven’s Progressive Matrices, features several rows of images with the final row missing its final image. To apply this test to AIs, the DeepMind researchers created a program that could generate unique matrix problems.

在人类世界里，我们使用相当易懂的视觉化智力测验评估抽象推理。其中一种受欢迎的测验名为「瑞文氏图形推理测验」，特征是在数行图像的最后一行、最后一格留下空白。为了将这套测验应用于人工智慧，DeepMind研究团队设计了一套可以生成唯一解矩阵问题的程式。

The results of the test weren’t great. Ultimately, the team’s AI IQ test shows that even some of today’s most advanced AIs can’t figure out problems we haven’t trained them to solve.

这项实验的结果并不好。最终，该团队的「人工智慧智力测验」结果显示，就连当今最先进的人工智慧，也无法解出我们从未训练它解决过的问题。

dictionary 新闻辞典 》

abstract：形容词，抽象的；名词，抽象、摘要。例句：Abstract thinking is the ability to think about things that are not actually present.（抽象思维指的是想像并未实际存在事物的能力。）

reasoning：名词，推理、论证。例句：Abstract reasoning is a hallmark of human intelligence.（抽象推理是人类智力的特点。）

matrix：名词，矩阵、模型。例句：A candidate is presented with a matrix of 3x3 geometric designs.（应试者会看到一个3乘3几何设计的矩阵。）

• DeepMind开创「人工智慧智力测验」，评估人工智慧的抽象推理能力。图为瑞文氏图形推理测验范例。（取自网路）