arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08274cs.CLcs.AIcs.LG
收藏

基于神经符号生成模型的进化组合符号学习

Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model

Massachusetts Institute of Technology(麻省理工学院)

Matthias Hofer, Tuan Anh Le, Roger Levy, Josh Tenenbaum

摘要:

人类有能力从有限的数据中快速理解丰富的组合概念。在这里,我们调查这种能力的背景下,听觉信号,这已经演变成一个文化传播实验,研究语言中组合结构的出现。我们提出了一个神经符号生成模型,它结合了以前概念学习方法的优点。我们的模型在神经网络方法上进行快速推理,同时仍然保留了结构化生成方法中有限数据的可解释性和泛化性。该模型在分类上优于纯粹基于神经网络的方法,如针对地面实况和人类实验分类偏好两者评估的,并且还产生观察到的信号的优异再现。我们的研究结果表明,灵活的组合神经符号架构的能力,在原始感知领域的人类一样的泛化,并提供了一个步骤,发展精确的计算模型的归纳偏见在语言进化。

英文摘要:

Humans have the ability to rapidly understand rich combinatorial concepts from limited data. Here we investigate this ability in the context of auditory signals, which have been evolved in a cultural transmission experiment to study the emergence of combinatorial structure in language. We propose a neuro-symbolic generative model which combines the strengths of previous approaches to concept learning. Our model performs fast inference drawing on neural network methods, while still retaining the interpretability and generalization from limited data seen in structured generative approaches. This model outperforms a purely neural network-based approach on classification as evaluated against both ground truth and human experimental classification preferences, and produces superior reproductions of observed signals as well. Our results demonstrate the power of flexible combined neural-symbolic architectures for human-like generalization in raw perceptual domains and offers a step towards developing precise computational models of inductive biases in language evolution.

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。

↑