Searching for Emergent Representations in Evolved Dynamical Systems

This paper reports an experiment in which artificial foraging agents with dynamic, recurrent neural network architectures, are "evolved" within a simulated ecosystem The resultant agents can compare different food values to "go for more," and display similar comparison performance to that found in biological subjects We propose and apply a novel methodology for analysing these networks, seeking to recover their quantity representations within an Approximationist framework We focus on Localist representation, seeking to interpret single units as conveying representative information through their average activities One unit is identified that passes our "representation test", representing quantity by inverse accumulation.