The evolution of representation in simple cognitive networks

DOI10.1162/NECO_A_00475zbMATH Open1448.92021arXiv1206.5771WikidataQ51219763 ScholiaQ51219763MaRDI QIDQ5378245FDOQ5378245

Authors: Lars Marstaller, Arend Hintze, Christoph Adami 

Publication date: 12 June 2019

Published in: Neural Computation (Search for Journal in Brave)

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.

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

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

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• A Mathematical Theory of Communication
• Probabilistic graphical models.
• Title not available (Why is that?)
• Multivariante information transmission
• Predictability, complexity, and learning
• Could information theory provide an ecological theory of sensory processing?
• Coherent infomax as a computational goal for neural systems
• Predictive information and explorative behavior of autonomous robots
• Information Theoretical Analysis of Multivariate Correlation
• Circuit minimization problem
• The Evolution of Representation in Simple Cognitive Networks
• Nonlinear neurons in the low-noise limit: a factorial code maximizes information transfer
• Power and limits of reactive agents

Cited In (7)

• MULTIPLE INTERACTING PROGRAMS: A REPRESENTATION FOR EVOLVING COMPLEX BEHAVIOR
• Title not available (Why is that?)
• The evolution of internal representation
• Title not available (Why is that?)
• The neuronal replicator hypothesis
• The robustness of zero-determinant strategies in iterated prisoner's dilemma games
• The Evolution of Representation in Simple Cognitive Networks

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)