Quantitative Aesthetics : Introduction to Machine Learning and Perceptual Machines for Design

This course aims to introduce students to concepts and techniques from Machine Learning and Computer Vision as a way to revisit questions of perception and aesthetics in the context of an AI mediated world and with its implications for creative work. Rather than focusing on large language based generative AI models we are going to explore the design potential and implications of some of their constituent components and the frameworks that enable them. Through a series of workshops and small projects student should develop an intuitive understanding of how model architecture, dataset curation, training and inference work and what are the opportunities for injecting creative intent beyond the use of language and prompt manipulation. The emphasis will be placed more on the perceptual capabilities and idiosyncrasies of ML models with some forays into proto-generative processes.

We will start with simple language embedding models to discuss the structure and operations on vector spaces that underly most ML applications. We will later introduce the classifier and autoencoder models as two archetypes of artificial percpetion and building blocks of other models. Through a series of targeted projects students will train and deploy these models to use them as surrogate perceptual systems that can curate, filter, organize and ultimately modify visual content.

The course will start with a brief introduction to Python and the relevant development environments and workflows. The ML library Pytorch and the Computer Vision Library OpenCV will form the basic technological stack.
 

Note regarding the Fall 2025 GSD academic calendar: The first day of classes, Tuesday, September 2nd, is held as a MONDAY schedule at the GSD. Courses that meet only on Tuesdays will meet for the first time on September 9th. Courses meet regularly otherwise. Please refer to the GSD academic calendar for additional details.