Graeme McCaig
In my PhD research I was building computer systems for artistic image generation/stylization using deep learning neural network technology. I am advancing new techniques for better fine-grained and fluid controllability of imagery, as well as computational modeling of the human emotional/aesthetic impact of different image qualities. Such advancements enable both “apprentice” AI software tools as well as as well as autonomous artificial artist systems.
Contact: r.graeme.mccaig@gmail.com
Position: PhD Researcher
Research
Deep Learning AI Creativity For Visuals / Words
Using Cognitive Science as a basis for our work, we attempt to model aspects of human creativity in AI. Specially we are using Neural Networks (and evolutionary systems) in the form of Deep Learning, CNNs, RNNs and other modern techniques to model aspects of human expression and creativity.
Cognitive (AI) Based Abstraction
What is abstraction? Can you use AI techniques to model the semantics of an idea, object, or entity, where that understanding allows for abstraction of the meaning? We use several AI techniques including genetic programming, Neural Nets and Deep Learning to explore abstraction in its many forms. Mainly here in the visual and narrative arts.
Publications
Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity
Journal Article: Procedia Computer Science, 2018
Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity
Conference Proceedings: International Conference on Computational Creativity, 2016
Paris, France
Using Artificial Intelligence Techniques to Emulate the Creativity of a Portrait Painter
Conference Proceedings: Electronic Visualisation and the Arts, British Computer Society, 2016
8 pages
London, UK
Adaptation of an Autonomous Creative Evolutionary System for Real-World Design Application Based on Creative Cognition
Conference Proceedings: Fourth International Conference on Computational Creativity, 2013
pp 40-47
Sydney, Australia