• Publications
  • Influence
Nonnegative Decomposition of Multivariate Information
TLDR
This work reconsider from first principles the general structure of the information that a set of sources provides about a given variable and proposes a definition of partial information atoms that exhaustively decompose the Shannon information in a multivariate system in terms of the redundancy between synergies of subsets of the sources. Expand
The Dynamics of Active Categorical Perception in an Evolved Model Agent
  • R. Beer
  • Psychology, Computer Science
  • Adapt. Behav.
  • 1 December 2003
TLDR
A model agent whose "nervous system" was evolved using a genetic algorithm to catch circular objects and to avoid diamond-shaped ones is studied to illustrate how the perspective and tools of dynamical systems theory can be applied to the analysis of situated, embodied agents capable of minimally cognitive behavior. Expand
On the Dynamics of Small Continuous-Time Recurrent Neural Networks
  • R. Beer
  • Computer Science
  • Adapt. Behav.
  • 1 March 1995
TLDR
This article begins a systematic examination of the dynamics of continuous-time recurrent neural networks with a fairly complete description of the possible dynamical behavior and bifurcations of one- and two-neuron circuits. Expand
Evolving Dynamical Neural Networks for Adaptive Behavior
TLDR
It is demonstrated that continuous-time recurrent neural networks are a viable mechanism for adaptive agent control and that the genetic algorithm can be used to evolve effective neural controllers. Expand
Dynamical approaches to cognitive science
  • R. Beer
  • Medicine, Psychology
  • Trends in Cognitive Sciences
  • 1 March 2000
TLDR
Three contrasting examples of work in this area that address the lexical and grammatical structure of language, Piaget's classic 'A-not-B' error, and active categorical perception in an embodied, situated agent are reviewed. Expand
The brain has a body: adaptive behavior emerges from interactions of nervous system, body and environment
  • H. Chiel, R. Beer
  • Medicine, Psychology
  • Trends in Neurosciences
  • 1 December 1997
TLDR
Computational neuroethology, which jointly models neural control and periphery of animals, is a promising methodology for understanding adaptive behavior. Expand
Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology
Foundations. Biological Background. The Artificial Insect. Locomotion Controller. Lesion Studies. Exploration. Feeding. Behavioral Choice. Discussion. Appendixes: Physical Parameters. NeuralExpand
Computational and dynamical languages for autonomous agents
  • R. Beer
  • Computer Science
  • 1 March 1996
TLDR
The issues nised and the ltsights gained go ditectly to the hea* of what it is to r derctanl krma cogtlitiott itself, and will be useful to anyone uonlning how dynanical approaches might be bro sht ta beat in thinkihg abo t asPects of h1lna11 casnitian. Expand
The dynamics of adaptive behavior: A research program
  • R. Beer
  • Computer Science
  • Robotics Auton. Syst.
  • 1 June 1997
TLDR
An initial mapping of the basic concepts of adaptive behavior into the language of dynamical systems theory is proposed, and some of the general consequences of this preliminary theoretical framework are discussed. Expand
A Dynamical Systems Perspective on Agent-Environment Interaction
  • R. Beer
  • Computer Science
  • Artif. Intell.
  • 1995
TLDR
A general theoretical framework for the synthesis and analysis of autonomous agents is sketched, in which an agent and its environment are modeled as two coupled dynamical systems whose mutual interaction is in general jointly responsible for the agent's behavior. Expand
...
1
2
3
4
5
...