Automation World published my article on validating control system ML models. It’s an exciting new area for life science automation, really challenging the established regulatory process.
Couldn’t be done alone. Thanks to Jacob Brunner and Marie Fiala for editing support and Eliott Park for laying the groundwork with his chromatography modeling.
Article is titled “Validating Automation Machine Learning Models – The Oracle Problem”. An excerpt:
“As adoption of machine learning (ML) and artificial intelligence (AI) on the plant floor becomes more common, it is becoming clear that the newly deployed machine models are subverting traditional testing techniques. It is not always possible, nor practical, to identify every possible execution path of a modern machine model developed through supervised learning. Protocols developed for traditional state-machine logic or sequences will require modernization to continue providing the same level of confidence.”