CS ManTech Workshop 2018
The theme of this year’s workshop is “Big Data – Data Storage – Data Retrieval – Machine Learning”.
In recent months, we have read stories about data being the new oil, artificial intelligence being the new electricity, that robots may take away the jobs of engineers or even doctors.
We, the compound semiconductor community, must ask what this all means for our industry! Picture how much data has been collected when a product device is delivered to our customers. Of the many million product devices tested daily, it is not uncommon to test more than 1000 electrical parameters on every single one. This product is assembled not only from a compound semiconductor device, like a power amplifier, but also from SMD components, filters, switches and power controllers. Along with product test, we collect data on each component during its manufacturing like tool data, SPC data or electrical tests like PCM or die sort.
In the morning we will discuss general aspects of data systems and their advantage in bridging the different areas of the manufacturing. The amount of data collected calls for an efficient way of storing and retrieving. We will cover two commonly used philosophies of storing and retrieving data: Relational Databases and Data Lakes.
The amount of data and the complexity of our product devices poses its challenges for data analysis, to solve yield problems and alike. One aspect of artificial intelligence is machine learning, which can clearly help in this scenario. In the afternoon we will introduce machine learning and its concepts followed by a review of statistical learning models in JMP, a widely used data analysis software.