Information-driven organization of visual receptive fields

Research output: Chapter in Book/Report/Conference proceedingConference contribution

51 Downloads (Pure)


By using information theory to reduce the state space of sensor arrays, such as receptive fields, for AI decision making we offer an adaptive algorithm without classical biases of hand coded approaches. This paper presents a way to build an acyclic directed graph to organise the sensor inputs of a visual receptive field. The Information Distance Metric is used to repeatedly select two sensors, which contain the most information about each other. Those are then encoded to a single variable, of equal alphabet size, with a deterministic mapping function that aims to create maximal entropy while maintaining a low information distance to the original sensors. The resulting tree determines which sensors are fused to reduce the input data while maintaining a maximum of information. The structure adapts to different environments of input images by encoding groups of preferred line structures or creating a higher resolution for areas with simulated movement. These effects are created without prior assumptions about the sensor statistics or the spatial configuration of the receptive field, and are cheap to compute since only pairwise informational comparison of sensors is used.
Original languageEnglish
Title of host publicationIn: Proceedings of the GWAL-8, 8th German Workshop on Artificial Life 2008
PublisherAkademische Verlagsgesellschaft
ISBN (Print)978-3-89838-613-5
Publication statusPublished - 2008


  • information theory
  • adaptive sensors


Dive into the research topics of 'Information-driven organization of visual receptive fields'. Together they form a unique fingerprint.

Cite this