精选理由
LeCun讲推理时优化是EBM和ODAI的根，连续变量用梯度优化，世界模型规划就是例子。
Yann LeCun在推文中指出，推理时优化是能量模型（EBM）和目标驱动AI（ODAI）的基础概念。当推理变量为连续值时，基于梯度的优化方法成为自然选择。基于世界模型的系统通过梯度优化进行规划，是ODAI的典型实例。
原文 · Yann LeCun
Using optimization at inference time is a foundational concept of Energy-Based Models (EBM) and Obje...
Using optimization at inference time is a foundational concept of Energy-Based Models (EBM) and Objective-Driven AI architectures (ODAI). When the variables to be inferred are continuous, it makes sense to use gradient-based optimization. A good instance of ODAI is world model-based systems that use gradient-based optimization for planning. 💬 6 🔄 5 ❤️ 51 👀 6236 📊 12 ⚡