用神经符号概念构建可持续学习与灵活推理的智能体
Neuro-Symbolic Concepts
- 用神经网络和符号程序融合表示物体、关系、动作等概念
- 支持零样本迁移与组合泛化，跨2D/3D/视频/机器人任务通用
- 适合需要持续学习与灵活推理的复杂智能体系统
本文提出一种以概念为中心的智能体构建范式，支持持续学习与灵活推理。该智能体使用神经符号概念词汇表，如物体、关系、动作等概念，这些概念基于感官输入与执行输出进行锚定，并具备组合性，可通过结构组合生成新概念。为促进学习与推理，概念采用类型化表示，结合符号程序与神经网络。利用此类神经符号概念，智能体可高效学习并重组解决跨领域任务，涵盖2D图像、视频、3D场景及机器人操作任务。该框架具备数据效率、组合泛化、持续学习与零样本迁移等优势。
原文摘要 · Abstract (English)
This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and action concepts, are grounded on sensory inputs and actuation outputs. They are also compositional, allowing for the creation of novel concepts through their structural combination. To facilitate learning and reasoning, the concepts are typed and represented using a combination of symbolic programs and neural network representations. Leveraging such neuro-symbolic concepts, the agent can efficiently learn and recombine them to solve various tasks across different domains, ranging from 2D images, videos, 3D scenes, and robotic manipulation tasks. This concept-centric framework offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。