1966
1996 - Diamantaras, K., and Kung, S. Y. Principal Component Neural Networks. New York: John Wiley and Sons, Inc.

NeuhausWhile the book by Diamantaras and Kung and the artist Max Neuhaus both deal with systems of perception and data structure, they represent distinct fields—computational neural science and sound art—that intersect in the study of human perception.

Principal Component Neural Networks (Diamantaras & Kung, 1996)

This text is a foundational technical resource on how Neural Networks can perform Principal Component Analysis (PCA).

It explores how neural models can take complex, high-dimensional data and extract the most significant patterns (principal components).Hebbian Learning: The authors present models based on Hebbian learning rules, where the "weights" of a network adapt based on input frequency and correlation—a mathematical parallel to how biological neurons learn.