Transparent Neural Networks

Integrating Concept Formation and Reasoning
  • Claes Strannegård
  • Olle Häggström
  • Johan Wessberg
  • Christian Balkenius
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7716)

Abstract

We present the transparent neural networks, a graph-based computational model that was designed with the aim of facilitating human understanding. We also give an algorithm for developing such networks automatically by interacting with the environment. This is done by adding and removing structures for spatial and temporal memory. Thus we automatically obtain a monolithic computational model which integrates concept formation with deductive, inductive, and abductive reasoning.

Keywords

transparent neural networks developmental robotics concept formation deductive reasoning inductive reasoning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Claes Strannegård
    • 1
    • 2
  • Olle Häggström
    • 3
  • Johan Wessberg
    • 4
  • Christian Balkenius
    • 5
  1. 1.Department of Philosophy, Linguistics and Theory of ScienceUniversity of GothenburgSweden
  2. 2.Department of Applied Information TechnologyChalmers University of TechnologySweden
  3. 3.Department of Mathematical SciencesChalmers University of TechnologySweden
  4. 4.Institute of Neuroscience and PhysiologyUniversity of GothenburgSweden
  5. 5.Department of PhilosophyLund UniversitySweden

Personalised recommendations