深度思维提出能量模型:5 例学会空间概念并跨域迁移
原标题:Learning concepts with energy functions
48AI 研判分
研究人员开发了一种基于能量的模型,仅需 5 个示例即可快速学习“近”、“上”等抽象空间概念。该模型不仅能在二维点集环境中识别和生成概念实例,还成功实现了从二维粒子环境到三维物理机器人的跨域知识迁移。这一成果展示了能量函数在少样本学习与具身智能中的潜力。
报道正文
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based robot.