Over the last decade, deep neural networks (DNNs) have transformed the state of the art in artificial intelligence. In domains such as language production and reasoning, long considered uniquely human abilities, contemporary models have proven capable of strikingly human-like performance. However, in contrast to classical symbolic models, neural networks can be inscrutable even to their designers, making it unclear what significance, if any, they have for theories of human cognition. Two extreme reactions are common. Neural network enthusiasts argue that, because the inner workings of DNNs do not seem to resemble any of the traditional constructs of psychological or linguistic theory, their success renders these theories obsolete and motivates a radical paradigm shift. Neural network skeptics instead take this inability to interpret DNNs in psychological terms to mean that their success is irrelevant to psychological science. In this article, we review recent work that suggests that the internal mechanisms of DNNs can, in fact, be interpreted in the functional terms characteristic of psychological explanations. We argue that this undermines the shared assumption of both extremes and opens the door for DNNs to inform theories of cognition and its development.

中文翻译：

---

深层神经网络如何为心理科学理论提供信息？


在过去的十年中，深度神经网络 (DNN) 改变了人工智能的最新技术。在语言产生和推理等领域，长期以来被认为是人类独有的能力，而现代模型已被证明能够具有惊人的类似人类的表现。然而，与经典符号模型相比，神经网络甚至对其设计者来说也可能是难以理解的，这使得人们不清楚它们对于人类认知理论有什么意义（如果有的话）。两种极端反应很常见。神经网络爱好者认为，由于 DNN 的内部工作原理似乎与任何传统的心理学或语言理论结构都不相似，因此它们的成功使这些理论变得过时，并引发了彻底的范式转变。相反，神经网络怀疑论者认为 DNN 无法用心理学术语解释，这意味着它们的成功与心理科学无关。在本文中，我们回顾了最近的工作，这些工作表明 DNN 的内部机制实际上可以用心理学解释的功能术语来解释。我们认为，这破坏了两个极端的共同假设，并为 DNN 为认知理论及其发展提供信息打开了大门。