基于脉冲神经网络的自主智能体可快速学习新概念并适应环境变化。
SNN-Based Online Learning of Concepts and Action Laws in an Open World
- 用脉冲神经网络构建生物启发式认知架构，实现语义记忆。
- 一击即学物体与动作概念，动作概念由三元组构成。
- 能泛化已有概念应对新情境，快速更新知识以适应变化。
我们提出一种完全自主的生物启发式认知代理，其核心为基于脉冲神经网络（SNN）的语义记忆系统。该代理在开放世界中自主探索，能够以一次性学习方式掌握物体/情境概念以及自身动作概念。物体与情境概念为单一属性，而动作概念则由初始情境、运动行为和结果三部分组成，体现代理对环境行动规律的理解。两类概念具有不同层次的泛化能力。决策时，代理通过查询语义记忆预测预期结果，并基于预测选择行动。实验表明，代理能借助先前学习的通用概念处理新情境，并迅速调整概念以适应环境变化。
原文摘要 · Abstract (English)
We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. This agent explores its universe and learns concepts of objects/situations and of its own actions in a one-shot manner. While object/situation concepts are unary, action concepts are triples made up of an initial situation, a motor activity, and an outcome. They embody the agent's knowledge of its universe's action laws. Both kinds of concepts have different degrees of generality. To make decisions the agent queries its semantic memory for the expected outcomes of envisaged actions and chooses the action to take on the basis of these predictions. Our experiments show that the agent handles new situations by appealing to previously learned general concepts and rapidly modifies its concepts to adapt to environment changes.
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。