Mirroring Action Generation and Recognition with Articulating Sensory–Motor Flow
Jun Tani · Oxford University Press eBooks · 2016
Abstract Chapter 8 introduces the RNNPB as a model of mirror neurons that have been considered to be crucially responsible for the composition and decomposition of actions. The RNNPB can learn a set of behavior primitives for generation as well as for recognition by means of error minimization in a predictive coding framework. The RNNPB model is evaluated through a set of robotics experiments whereby the following characteristics emerged. (1) The model can recognize aspects of a continuous perceptual flow by segmenting it into a sequence of chunks or reusable primitives, (2) a set of actional concepts can be learned with generalization by developing relational structures among those concepts internally as shown in the experiment on associative learning between protolanguage and actions, and (3) the model can generate not only learned behavior patterns but also novel ones by means of twists or dimples generated in the manifold of the RNNPB due to the potential nonlinearity of the network.