Biological evolution to inspire machine

A close-up of one of the generated results. Here, the bird-like patterns result from the 'eye' of the critic -- a network known as VGG19 -- used to compare the outputs of the competing networks, which is itself a model trained on classifying different natural images. Credit: Nicholas Guttenberg

IN a new study published in the journal Artificial Life, a research team led by Nicholas Guttenberg and Nathaniel Virgo of the Earth- Life Science Institute (ELSI) at Tokyo Institute of Technology, Japan, and Alexandra Penn of The Centre for Evaluation of Complexity Across the Nexus (CECAN), University of Surrey UK (CRESS), examine the connection between biological evolutionary open-endedness and recent studies in machine learning, hoping that by connecting ideas from artificial life and machine learning, it will become possible to combine neural networks with the motivations and ideas of artificial life to create new forms of open-endedness.