科技快讯｜电脑开始像人类一样推理

电脑开始像人类一样推理

Computers are starting to reason like humans

译者：地火 原文作者：Matthew Hutson 

How many parks are near the new home you’re thinking of buying? What’s the best dinner-wine pairing at a restaurant? These everyday questions require relational reasoning, an important component of higher thought that has been difficult for artificial intelligence (AI) to master. Now, researchers at Google’s DeepMind have developed a simple algorithm to handle such reasoning—and it has already beaten humans at a complex image comprehension test.

您想要购买的新家附近有多少个公园？餐厅最好的晚餐——葡萄酒配对是什么？这些日常问题需要关系推理，这是人工智能（AI）难以掌握的高级思想的重要组成部分。现在，Google DeepMind的研究人员已经开发了一种简单的算法来处理这种推理，而且它已经在复杂的图像理解测试中打败了人类。

Humans are generally pretty good at relational reasoning, a kind of thinking that uses logic to connect and compare places, sequences, and other entities. But the two main types of AI—statistical and symbolic—have been slow to develop similar capacities. Statistical AI, or machine learning, is great at pattern recognition, but not at using logic. And symbolic AI can reason about relationships using predetermined rules, but it’s not great at learning on the fly.

人类通常相当擅长关系推理，一种利用逻辑来联系和比较地点、序列和其他实体的思维。但是两种主要的人工智能技术——统计和符号——在类似的能力方面的发展非常缓慢。统计AI，也称为机器学习，在模式识别方面做的很棒，但是在逻辑方面则不然。而符号AI可以利用预定的规则来理解关系，在飞行中的学习能力却不好。

The new study proposes a way to bridge the gap: an artificial neural network for relational reasoning. Similar to the way neurons are connected in the brain, neural nets stitch together tiny programs that collaboratively find patterns in data. They can have specialized architectures for processing images, parsing language, or even learning games. In this case, the new “relation network” is wired to compare every pair of objects in a scenario individually. “We’re explicitly forcing the network to discover the relationships that exist between the objects,” says Timothy Lillicrap, a computer scientist at DeepMind in London who co-authored the paper.

新的研究提出了一种弥合差距的方法：一种关系推理的人工神经网络。类似大脑中神经元连接的方式，神经网络把微小的程序拼接到一起，协同在数据中寻找模式。它们有专门的架构以处理图像，分析语言甚至学习游戏。在这种情况下，新的“关系网络”被连接以逐个对比场景中的每一对对象。DeepMind在伦敦的计算机科学家Timothy Lillicrap表示：“我们明确驱使神经网络去发现物体之间的关系。”

He and his team challenged their relation network with several tasks. The first was to answer questions about relationships between objects in a single image, such as cubes, balls, and cylinders. For example: “There is an object in front of the blue thing; does it have the same shape as the tiny cyan thing that is to the right of the gray metal ball?” For this task, the relation network was combined with two other types of neural nets: one for recognizing objects in the image, and one for interpreting the question. Over many images and questions, other machine-learning algorithms were right 42% to 77% of the time. Humans scored a respectable 92%. The new relation network combo was correct 96% of the time, a superhuman score, the researchers report in a paper posted last week on the preprint server arXiv.

他和他的团队通过几个任务来挑战他们的关系网络。第一个是回答单张图片中物体之间的关系，如方块、球和圆柱体。“蓝色物体之前有一个东西，它和灰色金属球右边的微小青色物体形状一致吗？”对于这个任务，关系网络同其他两种神经网络结合在一起：一个是用来识别图片中的物体，另一个可以解释问题。在很多图片和问题中，其他的机器学习算法正确率为42%-77%。人类为92%，而新的网络获得了超过人类的分数：96%。研究者上周在预印网站arxiv上发布了这一报告。

The DeepMind team also tried its neural net on a language-based task, in which it received sets of statements such as, “Sandra picked up the football” and “Sandra went to the office.” These were followed by questions like: “Where is the football?” (the office). It performed about as well as its competing AI algorithms on most types of questions, but it really shined on so-called inference questions: “Lily is a Swan. Lily is white. Greg is a swan. What color is Greg?” (white). On those questions, the relation network scored 98%, whereas its competitors each scored about 45%. Finally, the algorithm analyzed animations in which 10 balls bounced around, some connected by invisible springs or rods. Using the patterns of motion alone, it was able to identify more than 90% of the connections. It then used the same training to identify human forms represented by nothing more than moving dots. 

DeepMind团队还在基于语言的任务中尝试了他们的神经网络，它接受一系列陈述句，如“Sandra拾起足球”和“Sandra去办公室”，接下来是以下问题：“足球在哪里？“（办公室）。它的表现和相竞争的AI算法一样好，但在所谓的推理问题上它确实表现出众：“莉莉是天鹅。莉莉是白色的。Greg是天鹅。Greg是什么颜色？“（白色）。在这些问题上，关系网络得分为98％，而其竞争对手则获得45％的分数。最后，该算法分析了其中10个球弹跳的动画，一些球通过不可见的弹簧或杆连接。仅使用运动模式分析，它就能识别超过90％的连接。然后使用相同的训练来识别由移动点所代表的人。

“One of the strengths of their approach is that it’s conceptually quite simple,” says Kate Saenko, a computer scientist at Boston University who was not involved in the new work but has also just co-developed an algorithm that can answer complex questions about images. That simplicity—Lillicrap says most of the advance is captured in a single equation—allows it to be combined with other networks, as it was in the object comparison task. The paper calls it “a simple plug-and-play module” that allows other parts of the system to focus on what they’re good at.

波士顿大学的计算机科学家凯特·桑科（Kate Saenko）说，“他们方法的一大优点就是其原理非常简单。”他没有参加的新的工作中但也参与开发了一个可以回答复杂图像问题的算法。Lillicrap说，这种采用一个公式所获得的简单性，使得其可以同其他的网络结合，就像对象比较的任务一样。论文称之为“一个简单的即插即用模块”，使得系统其他部分专注于各自擅长的内容。

“I was pretty impressed by the results,” says Justin Johnson, a computer scientist at Stanford University in Palo Alto, California, who co-developed the object comparison task­—and also co-developed an algorithm that does well on it. Saenko adds that a relation network could one day help study social networks, analyze surveillance footage, or guide autonomous cars through traffic.

加利福尼亚州帕洛阿尔托的斯坦福大学的计算机科学家贾斯汀·约翰逊（Justin Johnson）说，“结果让我印象很深刻。” 他共同开发了对象比较任务，同时也参与开发出了一个很好的算法。 Saenko补充说，关系网络有一天可以帮助学习社交网络，分析监控画面，或引导自动驾驶汽车通过车流。

To approach humanlike flexibility, though, it will have to learn to answer more challenging questions, Johnson says. Doing so might require comparing not just pairs of things, but triplets, pairs of pairs, or only some pairs in a larger set (for efficiency). “I’m interested in moving toward models that come up with their own strategy,” he says. “DeepMind is modeling a particular type of reasoning and not really going after more general relational reasoning. But it is still a superimportant step in the right direction.”

约翰逊说：为了获得像人一样的灵活性，还需要学习回答更有挑战性的问题。这样就要求不仅仅比较成对的事物，甚至三对，成对的对，或者仅仅一些更大的集合构成的对（为了效率起见）。“我对制定自己战略的模型很感兴趣”，他说，“DeepMind针对特定的推理建模，而不是追求通用关系推理。但它仍然是朝向正确方向的重要一步。”

版权声明：

本译文仅用于学习和交流目的。非商业转载请注明译者、出处，并保留文章在译言的完整链接。商业合作请联系 [email protected]   参考原文地址：http://www.sciencemag.org/news/2017/06/computers-are-starting-reason-humans

扫描二维码关注译言，获取优质译文资源，享受优质便捷的即时译服务。