The following two parallel pre-conference courses are taking place on Monday 22nd September at the Hilton Hotel. 

Please note that fees are £300 for those attending the full APACT Conference and £500 for those attending a course only. 

REGISTER NOW!

Pre-conference courses - Monday 22 September 2025
Title Non-linear Machine Learning for Calibration and Classification - Manny Palacios, Eigenvector Research Fundamentals of NIR PAT in Solid Dosage Pharmaceutical Manufacturing - Steve Hammond (Consultant) , Michael Reinhalter and Adam Rish, Sentronic US Corp
Description While linear machine learning methods, such as PLS regression, work in a very wide range of problems of chemical and biological interest, there are times when the relationships between variables are complex and require non-linear modeling methods. Many non-linear machine learning methods have been developed, however, we will focus on a few that we have found quite useful. The course begins with a discussion of linearizing transforms. Augmenting with non-linear transforms, e.g. polynomials, is discussed next. Locally Weighted Regression (LWR), Artificial Neural Networks (ANNs, including Deep-learning Networks) and Support Vector Machines (SVMs) are then considered, with SVMS for both regression and classification considered. Boosted regression and classification trees (XGBoost) and then covered. The course concludes with segments on how to choose a method and how to implement models online. The course includes hands-on computer time for participants to work example problems using PLS_Toolbox or Solo. This course seeks to provide attendees with an introduction to the theory and practice of near-infrared (NIR) spectroscopy applied to the analysis of solid samples in the pharmaceutical industry. The course will provide an overview of the fundamentals of NIR spectroscopy, discuss the challenges associated with analyzing and appropriately sampling streams of moving powders, provide an overview of common spectrometer and probe hardware used in the process environment, and introduce some common multivariate statistical methods used to extract process information from NIR spectra.
10.30 - 11.00 Registration
11.00 - 12.30
Introduction to Machine Learning
  • Nomenclature and Definitions
  • Methods: Unsupervised vs. Supervised
  • Bias vs. Variance Trade-off
  • Model Quality Metrics
Introduction to NIR and Sampling Fundamentals
  • Vibrational Spectroscopy Fundamentals
  • Diffuse Reflectance Fundamentals
  • Theory of Sampling Fundamentals
12.30 - 13.30 Lunch
13.30 - 15.00
Machine Learning Algorithms (Methods) - Part 1
  • Locally Weighted Regression
  • Support Vector Machines
  • Artificial Neural Networks
Chemometrics and NIR PAT Hardware
  • Chemometrics: Turning NIR Spectra into Process Information
  • Overview of Common Types of NIR PAT Systems
  • Discussion of spectrometer architecture
  • Discussion of process probes and their design
15.00 - 15.30 Tea & coffee
15.30 - 17.30
Machine Learning Algorithms (Methods) - Part 2 & Conclusion
  • Gradient Boosted Decision Trees (brief overview)
  • Model Fusion (Model Ensembles)
  • Choosing the Right Method
NIR PAT Practical Session
  • Practical NIR PAT Considerations
  • Instructor-lead Hands-On NIR PAT Demonstration
  • Question and Answer Session
17.30 Closing remarks / end of course

 

Fees are £300 for those attending APACT Conference and £500 for those attending a course only. 

REGISTER NOW!