arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.12201cs.AIcs.HCcs.LG
收藏

人类与机器中函数的组合学习

Compositional learning of functions in humans and machines

Meta AI

Yanli Zhou, Brenden M. Lake, Adina Williams

AI总结:

本研究开发视觉函数学习范式,发现人类能零样本泛化组合函数,且元学习组合性方法使Transformer模型模仿人类泛化模式。

摘要:

学习并组合函数的能力是人类高效学习与推理的基础,使得诸如根据已知烹饪过程创造新菜肴等灵活泛化成为可能。除了函数的顺序链接,现有语言学文献表明,人类能够掌握具有交互作用的更复杂组合,其中输出产生依赖于不同函数排序所引发的上下文变化。将研究扩展到视觉领域,我们开发了一种函数学习范式,以探索人类和神经网络模型在不同交互条件下学习并推理组合函数的能力。在对单个函数进行简短训练后,人类参与者被评估组合两个已学函数的方式,涵盖四种主要交互类型,包括第一个函数的应用创建或移除第二个函数应用上下文的情况。我们的研究结果表明,人类能够在各种交互条件下对新颖的视觉函数组合进行零样本泛化,展现出对上下文变化的敏感性。与神经网络模型在同一任务上的比较显示,通过元学习组合性(MLC)方法,标准的序列到序列Transformer可以模仿人类在组合函数时的泛化模式。

英文摘要:

The ability to learn and compose functions is foundational to efficient learning and reasoning in humans, enabling flexible generalizations such as creating new dishes from known cooking processes. Beyond sequential chaining of functions, existing linguistics literature indicates that humans can grasp more complex compositions with interacting functions, where output production depends on context changes induced by different function orderings. Extending the investigation into the visual domain, we developed a function learning paradigm to explore the capacity of humans and neural network models in learning and reasoning with compositional functions under varied interaction conditions. Following brief training on individual functions, human participants were assessed on composing two learned functions, in ways covering four main interaction types, including instances in which the application of the first function creates or removes the context for applying the second function. Our findings indicate that humans can make zero-shot generalizations on novel visual function compositions across interaction conditions, demonstrating sensitivity to contextual changes. A comparison with a neural network model on the same task reveals that, through the meta-learning for compositionality (MLC) approach, a standard sequence-to-sequence Transformer can mimic human generalization patterns in composing functions.

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。

↑