Network Pattern Processors

  • U. Grenander
Part of the Applied Mathematical Sciences book series (AMS, volume 24)


Imagine a hypothetical being — let us use the name Ω — living in an environment or microworld from which it receives sensory inputs. The pattern structure that Ω is confronted by is assumed unknown to start with and Ω will try to infer it as time goes on. In this chapter, we shall study one type of pattern processor constructed as a network of simple units. Our goal will be to find out how such a processor can be capable of pattern inference, to what extent this holds, and we shall look into both the normal and pathological operation of the network processor.


Experience Operator Learn Network Initial Network Binary Feature Sensory Space 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag New York Inc. 1978

Authors and Affiliations

  • U. Grenander
    • 1
  1. 1.Division of Applied MathematicsBrow UniversityProvidenceUSA

Personalised recommendations