论文标题
神经网络中概念的单元测试
Unit Testing for Concepts in Neural Networks
论文作者
论文摘要
从象征性概念方面，自然会理解许多复杂的问题。例如，我们的“猫”概念与我们的“耳朵”和“晶须”的概念以非承认方式有关。 Fodor（1998）提出了一种概念理论，该理论强调了通过选区结构相关的符号表示。神经网络是否与这样的理论一致。我们提出了用于评估系统行为是否与Fodor标准的几个关键方面一致的单元测试。使用简单的视觉概念学习任务，我们根据此规范评估了几种现代神经体系结构。我们发现，模型成功地测试了概念的基础，模块化和可重复性，但是有关因果关系的重要问题仍然开放。解决这些问题将需要新的方法来分析模型的内部状态。
Many complex problems are naturally understood in terms of symbolic concepts. For example, our concept of "cat" is related to our concepts of "ears" and "whiskers" in a non-arbitrary way. Fodor (1998) proposes one theory of concepts, which emphasizes symbolic representations related via constituency structures. Whether neural networks are consistent with such a theory is open for debate. We propose unit tests for evaluating whether a system's behavior is consistent with several key aspects of Fodor's criteria. Using a simple visual concept learning task, we evaluate several modern neural architectures against this specification. We find that models succeed on tests of groundedness, modularlity, and reusability of concepts, but that important questions about causality remain open. Resolving these will require new methods for analyzing models' internal states.
