Learn More
Tool use requires high levels of cognitive function and is only observed in higher mammals and some avian species such as corvids. In this paper, we will investigate how the capability to use tools can spontaneously emerge in a simulated evolution of a two degree-of-freedom articulated limb. The controller for the limb was evolved as neural circuits that(More)
Intelligence is a mixture of skills and knowledge: logic, sensorimotor skills, linguistic capability, mathematical skills, social skills, common sense knowledge , etc. What kind of test can cover most of these skills/knowledge while remaining concrete and grounded in the physical environment? It is helpful to see what scientists look for in animals as signs(More)
Recurrent neural networks (RNNs) often show very complicated temporal behavior. In this paper, we investigate the dynamics of a simple recurrent neural network used in a nontrivial articulated limb control task in a tool use domain. The RNN for the task is evolved by the NeuroEvolution of Augmenting Topologies (NEAT) algorithm. As a non-linear dynamical(More)
  • 1