认知温度计：用机器学习测量逻辑复杂度

1. 12:00
   arXiv · Computation and Language

   认知温度计：机器学习与逻辑复杂度

   论文提出把机器学习模型当作“认知温度计”，以更中立的方式测量语义复杂度，统一符号逻辑与连接主义 AI。逻辑与机器学习在相对复杂度及语义类型学效应上常得出收敛结果；二者分歧时，学习比逻辑复杂度更能解释现象。该方法旨在克服既有逻辑可定义性解释对逻辑语言选择高度敏感的问题。

Current heat 9·Comparable peak 10（Oct 9）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.