Intelligent encoding and economical communication in the visual stream

2004/03/16 by András Lörincz, Andras Lorincz, Lorincz, Andras
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Scientific Research and Philosophical Inquiry #cs.AI #cs.CC #nlin.AO #q-bio.NC

paper · pdf · doi:10.48550/arxiv.q-bio/0403022

6 pages, 2 figures

arxiv created 2004/03/16 · arxiv updated 2009/12/01

Abstract

The theory of computational complexity is used to underpin a recent model of neocortical sensory processing. We argue that encoding into reconstruction networks is appealing for communicating agents using Hebbian learning and working on hard combinatorial problems, which are easy to verify. Computational definition of the concept of intelligence is provided. Simulations illustrate the idea.

Related

• Debt-free intelligence: ecological information in minds and machines
• Some considerations on how the human brain must be arranged in order to make its replication in a thinking machine possible
• Information Processing by Neuron Populations in the Central Nervous System: A Theory of the Mathematical Structure of Data and Operations
• Efficient representation as a design principle for neural coding and computation
• On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence