错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

TON-ViT: A Neuro-Symbolic AI Based on Task Oriented Network with a Vision Transformer

  • Yupeng Zhuo,
  • Nina Jiang,
  • Andrew W. Kirkpatrick,
  • Kyle Couperus,
  • Oanh Tran,
  • Jonah Beck,
  • DeAnna DeVane,
  • Ross Candelore,
  • Jessica McKee,
  • Chad Gorbatkin,
  • Eleanor Birch,
  • Christopher Colombo,
  • Bradley Duerstock,
  • Juan Wachs

摘要

The objective of this paper is to present a neuro-symbolic AI based technique to represent field-medicine knowledge, referred as to TON-ViT. TON-ViT integrates a Deep Learning Model with an explicit symbolic manipulation, a task graph. This task graph describes the steps of each trauma resuscitation as denoted by a verb and noun pair. Through this representation, symbolic processing and manipulation on task graphs, we can find stereotypical procedures, regardless of style of the performer. Furthermore, we can use this technique to find differences in styles, errors, shortcuts and generate procedures never seen before. When used in combination with a transformer, it can help recognize actions in egocentric vision datasets. Last, through symbolic manipulations on the graph, it is possible to generate medical knowledge which the model has not seen before. We present preliminary results after testing the TON-ViT with the Trauma Thompson Dataset.