从人类和机器学习中的统计模式匹配中分离抽象
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
摘要：
获得抽象知识的能力是人类智能的标志，许多人认为这是人类与神经网络模型之间的核心差异之一。代理可以通过元学习被赋予对抽象的归纳偏见，在元学习中，他们被训练分配任务，这些任务共享一些可以学习和应用的抽象结构。然而，由于神经网络很难解释，因此很难判断代理是否已经学习了底层抽象，或者作为该抽象特征的统计模式。在这项工作中，我们比较了人类和代理的性能在Meta强化学习范式中，任务是从抽象规则生成的。我们定义了一种新的方法来构建“任务同色异谱”，紧密匹配的抽象任务的统计数据，但使用不同的底层生成过程，并评估性能的抽象和同色异谱任务。我们发现人类在抽象任务上的表现比同色异谱任务更好，而普通的神经网络架构在抽象任务上的表现通常比匹配的同色异谱差。这项工作为表征人类和机器学习之间的差异提供了基础，这些差异可以用于未来开发具有更像人类行为的机器的工作。
英文摘要：
The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed by many to be one of the core differences between humans and neural network models. Agents can be endowed with an inductive bias towards abstraction through meta-learning, where they are trained on a distribution of tasks that share some abstract structure that can be learned and applied. However, because neural networks are hard to interpret, it can be difficult to tell whether agents have learned the underlying abstraction, or alternatively statistical patterns that are characteristic of that abstraction. In this work, we compare the performance of humans and agents in a meta-reinforcement learning paradigm in which tasks are generated from abstract rules. We define a novel methodology for building "task metamers" that closely match the statistics of the abstract tasks but use a different underlying generative process, and evaluate performance on both abstract and metamer tasks. We find that humans perform better at abstract tasks than metamer tasks whereas common neural network architectures typically perform worse on the abstract tasks than the matched metamers. This work provides a foundation for characterizing differences between humans and machine learning that can be used in future work towards developing machines with more human-like behavior.
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。
