Foundation Model ColorMap, A Framework for Extracting and Visualizing the Foundation Models’ Color Knowledge

Foundation Model ColorMap, A Framework for Extracting and Visualizing the Foundation Models’ Color Knowledge

In April/May 2025, Christophe Hurter (ENAC, Toulouse) and I will present our latest research at the Computer Human Interface (CHI 2025) conference in Yokohama, Japan. Our work focuses on the extraction and analysis of the color-related knowledge embedded in recent AI systems, including deep learning...

Continue reading...
Self Organizing Map (SOM)

Self Organizing Map (SOM)

In 2014, the need for projection from multi-dimensional spaces toward 2D or 3D appears. From the 12 audio indicators provided by Echonest (now within spotify) to 2 dimensions or else 1 dimension. We had already used PCA (principal Component Analysis) but Self Organizing Map (SOM) and their algorithms were fascinating.

Continue reading...