Population based Mean of Multiple Computations networks: A building block for kinematic models

Abstract

Abstract-Population based encodings allow to represent probabilistic and fuzzy state estimates. Such a representation will be introduced and applied for the case of a redundant manipulator. Following the Mean of Multiple Computations principle, a neural network model (PbMMC) is presented in which the overall complexity is divided into multiple local relationships. This allows to solve inverse, forward and mixed kinematic problems. The local transformations in between the kinematic variables can be sufficiently well learned by small single MLP layers. The population codes of the kinematic variables are based on nested periodic receptive fields which allow to express multiple weighted state estimates. Therefore, the model as such is quite flexible as it can keep track of multiple possible solutions at the same time.

Setup of a Recurrent Neural Network as a Body Model for Solving Inverse and Forward Kinematics as well as Dynamics for a Redundant Manipulator

“…This encoding shows place-cell-like activations and fits well to recently described posture cells in rats [15]. Overall, the presented model addresses nicely different aspects on the neuronal organization of functional internal models: First, it shows a population-based encoding which in a next step might be exploited to encode noisy or faulty information in a probabilistic way [23]. Secondly, the MMC principle is based on redundant frames of reference as are assumed to be used inside the brain.…”