Adaptive Design of Experiments with machine learning
Date: Tuesday, 19 July 2022
Time: 16:00 UK time // 11.00 US East Coast
Speaker: Dr Joel Strickland, Materials Data Scientist, Intellegens
If you already registered for this event via LinkedIn, please check the email inbox of your LinkedIn-registered email address for joining instructions.
Or, for more details and to register, see below.
The development of new and improved chemicals and formulated products is costly and time-consuming due to the experimental programs required to explore all available chemistries, ingredients, and process options. Conventional Design of Experiments methods can narrow the options, but usually still result in significant experimental burdens. Machine learning could dramatically lessen this workload by analysing the available data and identifying the minimum set of experiments needed to achieve targets. But machine learning methods often fail when they analyse real-world, sparse, noisy experimental data.
In this webinar, Dr Joel Strickland will introduce Alchemite™, a novel machine learning method that supports adaptive experimental design, even when the input data is sparse and noisy. We’ll walk through a complete workflow for building a machine learning model, then improving it through focused acquisition of new data. Such an approach typically results in 50-80% fewer experiments than conventional methods, and has been proven in applications including specialty chemicals, food and beverage, paints, dyes, fragrances, cosmetics, and plastics
- Alchemite™ for chemistry and chemical processes
- Alchemite™ for formulation design
- Alchemite™ for design of experiments
- An overview of the Alchemite™ Technology
- Case studies
Subscribe to our newsletter to get the latest news on our other upcoming events.