Restricted Boltzmann Machine with Transformation Units in a Mirror Neuron System Architecture

In the mirror neuron system, the canonical neurons play a role in object shape and observer-object relation recognition. However, there are almost no functional models of canonical neurons towards the integration of these two functions. We attempt to represent the relative position between the object and the robot in a neural network model. Although at present some generative models based on the Restricted Boltzmann Machine can code the image transformation in continuous images, what we need to accomplish in canonical neuron modeling is different from the requirements of modeling transformation in video frames. As a result, we propose a novel model called “Restricted Boltzmann Machine with Transformation Units”, which can represent the relative object positions based on laser images. The laser sensor provides binary and accurate images and can further be connected with other models to construct a unified architecture of the mirror neuron system.