0


论监督学习技术在加速航空部件设计中的应用

On the Use of Supervised Learning Techniques to Speed up the Design of Aeronautics Components
课程网址: http://videolectures.net/mla09_bontempi_otuosl/  
主讲教师: Gianluca Bontempi
开课单位: 布鲁塞尔自由大学
开课时间: 2009-07-20
课程语种: 英语
中文简介:
复杂系统设计中的一个关键问题是评估大量潜在的替代设计。 因此,过于昂贵的评估过程可能主要在高维参数空间的情况下减慢对良好配置的搜索。 讲座将讨论使用机器学习技术加速评估和探索大型设计空间。 特别是,在加速热管设计,冷却的任务中评估和比较两种监督学习技术,前馈神经网络和懒惰学习通常用于航空和电子设备的设备。
课程简介: A crucial issue in the design of complex systems is the evaluation of a large number of potential alternative designs. A too expensive evaluation procedure can consequently slow down the search for good configurations mainly in the case of high dimensional parameter spaces. The talk will discuss the use of machine learning techniques for speeding up the evaluation and the exploration of large design spaces. In particular, two supervised learning techniques, feedforward neural networks and lazy learning, are assessed and compared in the task of accelerating the design of a heat-pipe, a cooling device commonly used in aeronautics and electronics.
关 键 词: 复杂系统设计; 替代设计; 机器学习技术
课程来源: 视频讲座网
最后编审: 2019-06-28:cjy
阅读次数: 52