Five Recent Papers

See also my complete list of papers

  1. Promoting Creative Design in Interactive Evolutionary Computation.
    (Forthcoming) T. Kowaliw, A. Dorin, and J. McCormack, IEEE Trans. on Evolutionary Computation, 2012
    We develop a notion of "creativity". We explore the definition via a generative art system, one based on ecosystems. Via a user study, we show validity of our notion of creativity relative to two control groups.

  2. Mechanisms for Complex Systems Engineering through Artificial Development.
    T. Kowaliw and W. Banzhaf, To appear in Springer's "Morphogenetic Engineering"
    A brief discussion of artificial development and why it is believed to work, especially two mechanisms: regularities and adaptive feedback. We summarize our own work using feedback in a design stage, using examples from structural engineering and a toy vasculogenesis problem.

  3. Evolving novel image features using Genetic Programming-based image transforms.
    T. Kowaliw, W. Banzhaf, N. Kharma, and S. Harding, IEEE CEC 2009
    We introduce a novel computer vision system, one designed to extract features from image databases. We explore the model on a muscular dystrophy-indicating cell image database. We show that the new extracted features outperform a standard set of pre-defined features in terms of classifying the cell images.

  4. Evolutionary Automated Recognition of an Individual's Artistic Style.
    T. Kowaliw, J. McCormack, and A. Dorin, IEEE CEC 2010
    We train our computer vision system to classify comic images by their originating artist. We then derive a distance function which can tell us, given some arbitrary image from google, how close it is to some given artist's style. Some objective evidence is presented that the function operates intuitively. Also: we release a new open database of artistic images.

  5. Environment as a Spatial Constraint on the Growth of Structural Form.
    T. Kowaliw, P. Grogono, and N. Kharma, GECCO 2007
    Exploration of an artificial development for the growth of structural design. The environment in which the designs were grown was perturbed, post-optimization: either be changing the amount of resources, or by changing the geometric shape. The growth procedure can adapt to changes in size, and some genomes can adapt to nearly any environmental geometry. These are artificial analogues to phenotypic robustness and phenotypic plasticity (polymorphism).