Speaker

AI-Based Diagnosis & Prediction Systems for Semiconductor Industry

A powerful generic AI technology is presented which allows the complete development of intelligent and automatable applications for reactive and predictive diagnosis with the ability to learn automatically. The Raptor technology contains all ingredients which are needed to build such applications on a very high and sophisticated level. The applications are modelled and stored as knowledge bases – and not programmed!
These applications rely on a hybrid AI architecture. Hybrid AI systems are programs that not only have learned from big data to solve a problem. Hybrid systems also take advantage from explicit domain and expert knowledge. They combine the capabilities of symbolic knowledge processing with the power of sub symbolic machine learning and the capabilities of data science. This approach makes hybrid AI applications not only more robust and powerful, but also explainable, comprehensive - and last but not least! auditable.
This technology can be applied to any kind of technical systems and processes. It is demonstrated using examples from semiconductor industry such as ‘Ion Implantation’, 'Defect Density Engineering', 'Deviation Analysis & Management' and others.