[论文解读] Deep Learning: A Critical Appraisal

Gary Marcus|arXiv (Cornell University)|Jan 2, 2018

Domain Adaptation and Few-Shot Learning参考文献 56被引用 387

一句话总结

本文批评深度学习，概述十个关切，并论证要实现人工通用智能需要用其他技术来补充深度学习。

ABSTRACT

Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) deep network model of Imagenet. What has the field discovered in the five subsequent years? Against a background of considerable progress in areas such as speech recognition, image recognition, and game playing, and considerable enthusiasm in the popular press, I present ten concerns for deep learning, and suggest that deep learning must be supplemented by other techniques if we are to reach artificial general intelligence.

研究动机与目标

• 促使对深度学习自复兴以来的快速进展进行批判性审视。
• 识别并明确深度学习的基本局限性和关切。
• 主张整合替代或补充性技术，以推动向人工通用智能发展。

提出的方法

• 通过列出十个关于深度学习的关切来提出结构化的批评。
• 提供有理有据的论证和实例来说明每个关切。
• 提倡将深度学习与互补的AI方法相结合的混合方法。

实验结果

研究问题

• RQ1 对当前深度学习发展轨迹的主要关切是什么？
• RQ2 单靠深度学习能否实现人工通用智能，还是需要用其他技术来补充？

主要发现

• 深度学习在若干领域取得进展，但存在显著的关切，限制了其能力。
• 本文主张需要补充性技术来推动向人工通用智能的进展。
• 批评强调需要比标准深度学习实践更广泛的方法论多样性。