Back to overview

A Framework of Relational Networks to Build Systems with Sensors able to Perform the Joint Approximate Inference of Quantities

Type of publication Peer-reviewed
Publikationsform Proceedings (peer-reviewed)
Author Martel Julien N.P., Cook Matthew,
Project Biological Information in Cortical Communication
Show all

Proceedings (peer-reviewed)

Title of proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop on Unconventional Comp
Place Hamburg
DOI 10.5167/uzh-121743


Probabilistic approaches such as Bayesian inference have been extensively used to design systems able to operate in environments under uncertainty. Implementing these approaches on real-world systems constrained in their latencies or in their power-budget is a challenge because of the general computational intensity required by such methods. In this work, we propose a very simple yet efficient framework to perform approximate inference in a network of quantities between which relations are specified a-priori. We present how we can take advantage of computational features of our framework to implement it in dedicated hardware devices such as GPGPUs or Cellular Processor Arrays (CPAs) for which we demonstrate a simple vision system instantiating the principles of our approach.