MAST3RBoost Project Participates in a Workshop on Big Data and Machine Learning in Microscopy

D.Gao gave an invited talk and F. Federici Canova contributed a tutorial workshop to the Machine Learning in Microscopy Workshop in Kanazawa. They focused on how modern research techniques have massively increased our ability to generate large quantities of data. This data can be leveraged with data science, machine learning, and automation techniques. Several examples were showcased including modules developed within the Mast3rboost project such as active learning tables, materials maps, and integrated data analysis tools. Furthermore, the LabCore digital research platform and ALANN graphical user interface are being developed to combine data management and machine learning tools with instrument control and automation capabilities for the scanning probe community.

The tutorial session offered a basic introduction to machine learning (ML) techniques for image analysis. Essential ML concepts and model training procedures were outlined using PyTorch before practical implementations were demonstrated, showcasing the use of a Convolutional Neural Network (CNN) for classification tasks, with high-resolution AFM images as an illustrative example. The tutorial equipped participants with practical knowledge that can be readily applied to their own microscopy problems.