arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.08034cs.LGcs.CVq-bio.NCstat.ML
收藏

人们仅仅从几个例子中推断出递归的视觉概念

People infer recursive visual concepts from just a few examples

New York University(纽约大学);University of California Berkeley(加州大学伯克利分校)

Brenden M. Lake, Steven T. Piantadosi

摘要:

机器学习在对图像中的对象进行分类方面取得了重大进展,但最好的算法忽略了人们如何学习和思考类别的重要方面。人们可以从更少的例子中学习更丰富的概念,包括解释类别成员如何形成的因果模型。在这里,我们探索这种人类能力的限制,推断因果“程序”-潜在的生成过程与非平凡的算法属性-从一个,两个或三个视觉的例子。人们被要求以几种方式推断程序,既分类又产生新的例子。作为这些归纳能力的理论,我们提出了一个贝叶斯程序学习模型,搜索空间的程序的最佳解释的意见。虽然变量,但人们的判断与模型大致一致,与几种替代方案不一致,包括用于对象识别的预训练深度神经网络,这表明人们可以从稀疏的输入数据中学习和推理丰富的算法抽象。

英文摘要:

Machine learning has made major advances in categorizing objects in images, yet the best algorithms miss important aspects of how people learn and think about categories. People can learn richer concepts from fewer examples, including causal models that explain how members of a category are formed. Here, we explore the limits of this human ability to infer causal "programs" -- latent generating processes with nontrivial algorithmic properties -- from one, two, or three visual examples. People were asked to extrapolate the programs in several ways, for both classifying and generating new examples. As a theory of these inductive abilities, we present a Bayesian program learning model that searches the space of programs for the best explanation of the observations. Although variable, people's judgments are broadly consistent with the model and inconsistent with several alternatives, including a pre-trained deep neural network for object recognition, indicating that people can learn and reason with rich algorithmic abstractions from sparse input 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。

↑