Date/time: 24 April // 16:00 UK time // 11:00 US East
If you have registered for this event via LinkedIn, please check the email address associated with your LinekedIn account for joining instructions. Otherwise, please register below.
Machine learning accelerates innovation in chemicals, materials, life sciences, and manufacturing by delivering deep data insights, guiding experiment, and finding new solutions to complex optimization problems. But just getting started can be difficult. There are many challenges in building a machine learning model from real, messy, experimental or process data. In this webinar, we’ll outline some of those difficulties and how they are overcome in the Alchemite Suite software. We’ll discuss issues such as handling missing data, uncertainty in both the model and experimental measurements, and coping with data types such as categoricals and ordinals. We’ll show how Alchemite overcomes such challenges to make building and applying a machine learning model a simple process, possible in a few button-clicks, and we’ll demonstrate some new features, designed based on user feedback, that fine-tune this process.