arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.06994cs.LGcs.AIcs.SC
收藏

系统的人类学习和概括从一个简短的教程与解释性反馈

Systematic human learning and generalization from a brief tutorial with explanatory feedback

Stanford University(斯坦福大学)

Andrew J. Nam, James L. McClelland

摘要:

长期以来,神经网络一直被用于模拟人类智能,捕捉行为和认知的元素及其神经基础。深度学习的最新进展使神经网络模型在许多方面达到甚至超过了人类的智力水平,但与人类不同的是,它们快速学习新任务的能力仍然是一个挑战。人们不仅可以在熟悉的领域进行推理,而且还可以通过新的问题和情况快速学习推理,这就提出了一个问题:现代神经网络模型在多大程度上捕捉了人类智能,以及它们在哪些方面存在分歧。在这项工作中,我们探讨了这一差距,调查人类成年人的能力,学习抽象推理任务的基础上,数独从一个简短的教学教程与解释性反馈不正确的反应,使用范围狭窄的训练样本。我们发现,掌握任务的参与者在少量的试验中做到了这一点,并且很好地概括了训练范围之外的谜题。我们还发现,大多数掌握任务的人可以描述一个有效的解决方案的策略,这样的参与者表现更好的转移难题比那些策略描述是模糊或不完整的。有趣的是,只有不到一半的人类参与者成功地获得了有效的解决方案策略,而这种能力与高中数学教育有关。我们认为,这些研究结果构成的挑战,建立计算模型,捕捉我们的研究结果的各个方面,并指向一个可能的角色,学习从事基于推理的推理,以支持快速学习和泛化。

英文摘要:

Neural networks have long been used to model human intelligence, capturing elements of behavior and cognition, and their neural basis. Recent advancements in deep learning have enabled neural network models to reach and even surpass human levels of intelligence in many respects, yet unlike humans, their ability to learn new tasks quickly remains a challenge. People can reason not only in familiar domains, but can also rapidly learn to reason through novel problems and situations, raising the question of how well modern neural network models capture human intelligence and in which ways they diverge. In this work, we explore this gap by investigating human adults' ability to learn an abstract reasoning task based on Sudoku from a brief instructional tutorial with explanatory feedback for incorrect responses using a narrow range of training examples. We find that participants who master the task do so within a small number of trials and generalize well to puzzles outside of the training range. We also find that most of those who master the task can describe a valid solution strategy, and such participants perform better on transfer puzzles than those whose strategy descriptions are vague or incomplete. Interestingly, fewer than half of our human participants were successful in acquiring a valid solution strategy, and this ability is associated with high school mathematics education. We consider the challenges these findings pose for building computational models that capture all aspects of our findings and point toward a possible role for learning to engage in explanation-based reasoning to support rapid learning and generalization.

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。

↑