I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a "harness"), running at inference time, orchestrating thousands of calls to a neural network for any given task, is the exact definition of a "neurosymbolic architecture"
AI 导读
我本以为这是显而易见的，但以防万一还是说明一下：一个百万行代码库（也称为“harness”），在推理时运行，为任何给定任务编排对神经网络的数千次调用，这正是“神经符号架构”的确切定义。
I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a "harness"), running at inference time, orchestrating thousands of calls to a neural network for any given task, is the exact definition of a "neurosymbolic architecture"
来源：François Chollet· x.com