【24h】

Integrating research into the core curriculum. A case study

机译:将研究纳入核心课程。案例研究

获取原文

摘要

Summary form only given. This presentation describes an approachto providing undergraduates with a “real-world” researchexperience within the context of a core computer science course. As arequired course, Introduction to Artificial Intelligence (AI) istypically taught in the junior/senior year, and normally coversfundamental topics in AI as well as Lisp programming. The author wantedto give the students an experience of what is involved in a real AIresearch project, such as the Visual Interaction Assistant forRadiology. This intelligent assistant is based on extensive cognitivedata collection from radiologists reading chest X-rays, and there areseveral open analysis problems which still need to be resolved. Itseemed that the “think aloud” reports of the radiologistscould be used as a vehicle to help the students learn how to extractcomputationally meaningful information from a domain expert's thoughtsand words. Many issues arising in this exercise are applicable to thedevelopment of expert systems in other domains as well, for example:handling specialized vocabulary, developing quantitative measures andqualitative concept labeling procedures, applying subjective ratings,aggregating data, and interpreting results of the analyses bothindividually and in the context of the whole experiment. The requiredtasks included a time analysis using the original video data, a conceptanalysis where the words in the protocols were categorized and labeled,and a performance analysis where the subjects' diagnoses were comparedwith those of the project expert
机译:仅提供摘要表格。本演示文稿介绍了一种方法 为大学生提供“真实世界”的研究 在核心计算机科学课程中的经验。作为一个 必修课,《人工智能入门》是 通常在大三/大三期间教书,通常涵盖 AI和Lisp编程的基本主题。作者想要 让学生体验真正的人工智能所涉及的内容 研究项目,例如用于 放射学。这个智能助手基于广泛的认知 放射科医生读取胸部X射线的数据收集,并且有 几个尚待解决的开放分析问题。它 似乎放射科医生的“大声思考”报告 可以用作帮助学生学习如何提取的工具 来自领域专家思想的对计算有意义的信息 和文字。此练习中出现的许多问题都适用于 还开发其他领域的专家系统,例如: 处理专业词汇,制定量化措施,以及 定性概念标签程序,应用主观评分, 汇总数据并解释分析结果 在整个实验的范围内单独进行。所需的 任务包括使用原始视频数据进行时间分析, 分析协议中单词的分类和标记位置, 以及对受试者诊断进行比较的绩效分析 与项目专家一起

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号