Paper: “Cognitive systems evolve complex representations for adaptive behavior”

A block moving diagonally across the agents retina leaves different patterns.

How do brains store information about their environment, and how much?

How do you measure which features of a world are represented in a brain, and what concepts a brain uses to make decisions?

Lars Marstaller et al. explore these questions in a recent contribution from the Adami lab.

URL: http://arxiv.org/abs/1206.5771

 
 

Abstract

Representations are internal models of the world that provide context to a sensory stream and are formed over evolutionary time as well as learned. We argue here that representations are the expected consequence of an adaptive process, give a formal definition of representation based on information theory, and quantify it using our new measure R. To measure how R changes over time, we evolve two types of networks—a recurrent artificial neural network and a network of hidden Markov gates—to solve a categorization task using a Genetic Algorithm. We find that the capacity to represent increases during evolutionary adaptation and that representations build up during the lifetime of these agents. We examine the concepts that are being represented, how they are logically encoded in the networks, and how they form as an agent behaves to solve a task. We conclude that any successful cognitive system that represents its environment within internal states should have a positive R.

1 Comment

  1. […] How do brains store information about their environment, and how much? How do you measure which features of a world are represented in a brain, and what concepts a brain uses to make decisions? Lars Marstaller et al.  […]

Leave a Reply

  • Adami Lab Schedule

    September  2017
    MTWTFSS
     123
    45678910
    11121314151617
    18192021222324
    252627282930