MACHINE LEARNING CURATION
ABOUT THIS SERIES
This series of paintings is my first use of machine learning as a technology to curate and classify painting compositions. I use machine learning software to supervise to extract shapes from my existing abstract paintings, automate creating new compositions and then curate which ones I will like most. This software has created over 40,000 compositions to process. I have been testing different classification processes while developing new ways of processing the paintings including: Linear Regression, Random Forests, Decision Trees, K-Means clusters, and TensorFlow. Although I am using machine learning, the most fascinating aspect of the project for me is how much I am learning about my personal subjective preferences and abstract composition.
It has also been interesting documenting the learning process through the act of painting. Painting is seen as a valuable, resource intensive process, while software development is quick. I am spending resources painting results of instantaneous calculations that are in development.
The paintings are titled based on Google’s untrained TensorFlow Inception Classification model. Untrained means it is downloaded from Google and that I have not trained the model for my specific task. Their model classifies images to objects, so the software suggest what the abstract painting is. It is interesting to take a second look at abstract art and consider how its been seen by the code. For example, hockey puck, bird house, sweet potato, bulletproof vest are only some of the objects it has found in the paintings. If you want to learn more about this process check out this page.