arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.06126cs.CV
收藏

卷积神经网络有多智能?

How intelligent are convolutional neural networks?

Siemens Medical Solutions USA, Inc.(西门子医疗解决方案美国公司)

Zhennan Yan, Xiang Sean Zhou

摘要:

受完形模式理论和Winograd语言理解挑战赛的启发,我们设计了合成实验来研究深度学习算法从示例中推断简单(至少对人类来说)视觉概念(如对称性)的能力。视觉概念由随机生成的正面和负面示例图像表示。然后,我们测试算法(和人类)从这些图像中学习概念的能力和速度。训练和测试是在多轮中逐步进行的,随后的每一轮都故意设计得比前一轮更复杂和混乱,特别是如果学习者没有掌握概念。然而,如果这个概念被理解,所有故意的测试都会变得简单。我们的实验表明,人类通常可以在只看很少数量的例子后快速推断出语义概念(这通常被称为“啊哈时刻”:突然意识到的时刻),并且在所有测试回合中都表现完美(除了粗心的错误)。相反,深度卷积神经网络(DCNN)可以在统计上近似一些概念,但只有在看到更多(x10^4)的例子之后。它仍然会犯明显的错误,特别是在故意的测试回合或训练分布之外的样本上。这表明缺乏真正的“理解”,或者未能达到正确的语义“公式”。我们确实发现有些概念对于DCNN来说比其他概念更容易。例如,简单的“计数”比“对称性”更容易学习,而“一致性”或“一致性”对于DCNN来说更难学习。最后,我们提出了一个“啊哈挑战”的视觉感知,呼吁集中和定量研究完形风格的机器智能使用有限的训练样本。

英文摘要:

Motivated by the Gestalt pattern theory, and the Winograd Challenge for language understanding, we design synthetic experiments to investigate a deep learning algorithm's ability to infer simple (at least for human) visual concepts, such as symmetry, from examples. A visual concept is represented by randomly generated, positive as well as negative, example images. We then test the ability and speed of algorithms (and humans) to learn the concept from these images. The training and testing are performed progressively in multiple rounds, with each subsequent round deliberately designed to be more complex and confusing than the previous round(s), especially if the concept was not grasped by the learner. However, if the concept was understood, all the deliberate tests would become trivially easy. Our experiments show that humans can often infer a semantic concept quickly after looking at only a very small number of examples (this is often referred to as an "aha moment": a moment of sudden realization), and performs perfectly during all testing rounds (except for careless mistakes). On the contrary, deep convolutional neural networks (DCNN) could approximate some concepts statistically, but only after seeing many (x10^4) more examples. And it will still make obvious mistakes, especially during deliberate testing rounds or on samples outside the training distributions. This signals a lack of true "understanding", or a failure to reach the right "formula" for the semantics. We did find that some concepts are easier for DCNN than others. For example, simple "counting" is more learnable than "symmetry", while "uniformity" or "conformance" are much more difficult for DCNN to learn. To conclude, we propose an "Aha Challenge" for visual perception, calling for focused and quantitative research on Gestalt-style machine intelligence using limited training examples.

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。

↑