Perr-Sauer, Jordan. “Observing Integrated Information in Artificially Evolved Neural Networks.” (2009).
URL1 URL2
Evolution has proven to be a wildly successful autonomous process for creating intelligent systems in the natural world and in simulation. Since the early 1960s, researchers have used artificial evolution to find ingenious and novel solutions to complex problems such as series prediction and flight control. Recently, artificial evolution has been applied to neural networks with the aim of evolving more robust artificial intelligence. Several metrics have been proposed to chart the emergence of intelligence in these evolved networks. This work analyzes the behavior of a new metric, integrated information (φ). Observed data is analyzed, interpreted, and compared to more conventional properties of the artificial neural network. The data analysis shows that φ increases over evolutionary time and is therefore promising as a heuristic measure.