Automated learning of model classifications

Cheuk Yiu Ip, William C. Regli, Leonard Sieger, Ali Shokoufandeh
2003 Proceedings of the eighth ACM symposium on Solid modeling and applications - SM '03  
This paper describes a new approach to automate the classification of solid models using machine learning techniques. Existing approaches, based on group technology, fixed matching algorithms or pre-defined feature sets, impose a priori categorization schemes on engineering data or require significant human labeling of design data. This paper describes a shape learning algorithm and a general technique for "teaching" the algorithm to identify new or hidden classifications that are relevant in
more » ... t are relevant in many engineering applications. In this way, the core shape learning algorithm can be used to find a wide variety of model classifications based on user input and training data. This allows for great flexibility in search and data mining of engineering data.
doi:10.1145/781650.781659 fatcat:s3w3f2cfhvfenid4cn5cis7kry