The evolution of representation in simple cognitive networks

DOI10.1162/NECO_A_00475MaRDI QIDQ5378245zbMATHWikidataFDO

Authors Lars Marstaller, Arend Hintze, Christoph Adami

Publication date 12 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1206.5771

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: Representations are internal models of the environment that can provide guidance to a behaving agent, even in the absence of sensory information. It is not clear how representations are developed and whether or not they are necessary or even essential for intelligent behavior. We argue here that the ability to represent relevant features of the environment is the expected consequence of an adaptive process, give a formal definition of representation based on information theory, and quantify it with a measure R. To measure how R changes over time, we evolve two types of networks---an 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 agents form representations of their environment during their lifetime. This ability allows the agents to act on sensorial inputs in the context of their acquired representations and enables complex and context-dependent behavior. We examine which concepts (features of the environment) our networks are representing, how the representations are logically encoded in the networks, and how they form as an agent behaves to solve a task. We conclude that R should be able to quantify the representations within any cognitive system, and should be predictive of an agent's long-term adaptive success.

Recommendations

• The evolution of internal representation
• MULTIPLE INTERACTING PROGRAMS: A REPRESENTATION FOR EVOLVING COMPLEX BEHAVIOR
• Representations of Space and Time in the Maximization of Information Flow in the Perception-Action Loop
• On the evolution of learning: Representation of a stochastic environment
• The neuronal replicator hypothesis

Cites work

• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 867338 (Why is no real title available?)
• A Mathematical Theory of Communication
• Circuit minimization problem
• Coherent infomax as a computational goal for neural systems
• Could information theory provide an ecological theory of sensory processing?
• Information Theoretical Analysis of Multivariate Correlation
• Multivariante information transmission
• Nonlinear neurons in the low-noise limit: a factorial code maximizes information transfer
• Power and limits of reactive agents
• Predictability, complexity, and learning
• Predictive information and explorative behavior of autonomous robots
• Probabilistic graphical models.
• The evolution of representation in simple cognitive networks

Cited in

(8)

• scientific article; zbMATH DE number 2013448 (Why is no real title available?)
• The neuronal replicator hypothesis
• The robustness of zero-determinant strategies in iterated prisoner's dilemma games
• The evolution of internal representation
• scientific article; zbMATH DE number 1900806 (Why is no real title available?)
• The evolution of representation in simple cognitive networks
• Autocatalytic networks in cognition and the origin of culture
• MULTIPLE INTERACTING PROGRAMS: A REPRESENTATION FOR EVOLVING COMPLEX BEHAVIOR

This page was built for publication: The evolution of representation in simple cognitive networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5378245)