比较监督学习动态:深度神经网络与人类数据效率相当,但存在泛化滞后
Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag
AI总结:
该研究通过构建对齐学习条件的受限监督环境,对比人类与多种深度神经网络的图像分类学习动态,发现二者数据效率相当,但DNNs存在泛化滞后,人类可直接习得可泛化表征,挑战了领域内的普遍假设。
摘要:
近期研究中,已有大量针对人类与深度神经网络(DNNs)在图像分类领域的行为比较。这类比较研究通常聚焦于学习过程的最终结果,即衡量并比较二者在形成物体类别表征后的相似性。然而,对于这些表征如何产生的过程——也就是学习过程中观察到的行为变化与中间阶段——较少有直接的实证比较。本文对人类观察者与多种经典及前沿DNNs的学习动态展开了详细研究。我们构建了一个受限监督学习环境,以对齐起始点、输入模态、可用输入数据及所提供反馈等与学习相关的条件。在整个学习过程中,我们评估并比较了习得的表征向未见过的测试数据泛化的效果。全学习过程的比较结果显示,DNNs展现出与人类学习者相当的数据效率,这对该领域的一些普遍假设提出了挑战。但我们的结果也揭示了二者的表征差异:DNNs的学习具有显著的泛化滞后特征,而人类似乎能立即获得可泛化的表征,无需先经历一个仅学习训练集特定信息、之后再迁移到新数据的预备阶段。
英文摘要:
Recent research has seen many behavioral comparisons between humans and deep neural networks (DNNs) in the domain of image classification. Often, comparison studies focus on the end-result of the learning process by measuring and comparing the similarities in the representations of object categories once they have been formed. However, the process of how these representations emerge -- that is, the behavioral changes and intermediate stages observed during the acquisition -- is less often directly and empirically compared. Here we report a detailed investigation of the learning dynamics in human observers and various classic and state-of-the-art DNNs. We develop a constrained supervised learning environment to align learning-relevant conditions such as starting point, input modality, available input data and the feedback provided. Across the whole learning process we evaluate and compare how well learned representations can be generalized to previously unseen test data. Comparisons across the entire learning process indicate that DNNs demonstrate a level of data efficiency comparable to human learners, challenging some prevailing assumptions in the field. However, our results also reveal representational differences: while DNNs' learning is characterized by a pronounced generalisation lag, humans appear to immediately acquire generalizable representations without a preliminary phase of learning training set-specific information that is only later transferred to novel data.
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。