arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.02356cs.CVcs.AI
收藏

心理模拟的神经-符号框架

A Neural-Symbolic Framework for Mental Simulation

Universität der Bundeswehr München(慕尼黑联邦国防军大学)

Michael Kissner

摘要:

我们提出了一个神经符号框架,用于观察环境,并不断学习视觉语义和直观的物理学,以在交互式模拟中重现它们。该框架由五个部分组成,一个神经-符号混合网络的基础上胶囊逆图形,一个情景记忆存储观察,直观的物理交互网络,元学习代理,不断提高框架和查询语言,作为框架的接口模拟。通过终身元学习,胶囊网络不断扩展和训练,以便在每次迭代中更好地适应其环境。这使得它能够使用Few-Shot方法学习新的语义,并且在其生命周期中从Oracle获得的输入最少。通过观察,直觉物理学部分推断出场景中物体的所有必要物理属性,从而实现预测。最后,一个自定义的查询语言将所有部分联系在一起,它允许执行各种心理模拟任务,如导航,排序和模拟游戏环境,我们说明了我们的新方法的潜力。

英文摘要:

We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation. The framework consists of five parts, a neural-symbolic hybrid network based on capsules for inverse graphics, an episodic memory to store observations, an interaction network for intuitive physics, a meta-learning agent that continuously improves the framework and a querying language that acts as the framework's interface for simulation. By means of lifelong meta-learning, the capsule network is expanded and trained continuously, in order to better adapt to its environment with each iteration. This enables it to learn new semantics using a few-shot approach and with minimal input from an oracle over its lifetime. From what it learned through observation, the part for intuitive physics infers all the required physical properties of the objects in a scene, enabling predictions. Finally, a custom query language ties all parts together, which allows to perform various mental simulation tasks, such as navigation, sorting and simulation of a game environment, with which we illustrate the potential of our novel approach.

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。

↑