“Guess, Check and Fix: a Phenomenology of Improvisation in ‘Neural’ Painting”, Suk Kyoung Choi2018-02-22 (CNN)⁠:

The parameter space offered by neural network image synthesis offers a creative environment that is little understood and quite literally emergent. In an attempt to come to terms with this space, an artist enters into an improvisational reflection on ‘neural painting’, made possible with what are called style transfer algorithms.

Artistic painting offers access to transitional states existing at the interstices of expression and reflection in the creative process. Of all the conceptual dimensions offered by neural style transfer models (where the ‘content’ of one source is blended with the ‘style’ of another), the convolutional blending of ‘content weight’ offers a fertile metaphor for artistic painting phenomenology, providing a tool for the investigation of stylistic schema in the iterative, improvisational movement from concept to representation.

A preliminary phenomenological framework describing the process of neural painting is developed, offering an art-as-research perspective on inter-subjectively positioned creativity support technology.

[Keywords: Art process, embodied cognition, reflective practice, AI art, J. G. Ballard]

See Also:

• “Generative Art Using Neural Visual Grammars and Dual Encoders”

• “Visual Attribute Transfer through Deep Image Analogy”

• “Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models”

• “StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis”

• “Paint by Word”