Computational Evolutionary Perception

  title={Computational Evolutionary Perception},
  author={Donald D. Hoffman and Manish Singh},
  pages={1073 - 1091}
Marr proposed that human vision constructs “a true description of what is there”. He argued that to understand human vision one must discover the features of the world it recovers and the constraints it uses in the process. Bayesian decision theory (BDT) is used in modern vision research as a probabilistic framework for understanding human vision along the lines laid out by Marr. Marr's contribution to vision research is substantial and justly influential. We propose, however, that evolution by… 

Figures from this paper

Natural Selection and Shape Perception

This Computational Evolutionary Perception (CEP) framework also incorporates fitness in a fundamental way, and it allows us to consider different possible relationships between the objective world and perceptual representations (e.g., in evolving visual systems).

The Interface Theory of Perception

It is found that veridical perceptions—strategies tuned to the true structure of the world—are routinely dominated by nonveridical strategies tuned to fitness.

Fitness Beats Truth in the Evolution of Perception

The FBT Theorem provides a quantitative measure of the extent to which the fitness-only strategy dominates the truth strategy, and of how this dominance increases with the size of the perceptual space.

1 Objects of Consciousness

Current models of visual perception typically assume that human vision estimates true properties of physical objects, properties that exist even if unperceived. However, recent studies of perceptual

Objects of consciousness

This work develops the dynamics of interacting conscious agents, and study how the perception of objects and space-time can emerge from such dynamics, and shows that one particular object has a wave function that is identical in form to the harmonic functions that characterize the asymptotic dynamics of conscious agents.

Natural Selection and Shape Perception : Shape as an Effective Code for Fitness

Our perception of shape is, like all of our perceptions, a pro duct of evolution by natural selection. This entails that our perception of shap e is a satisficing solution to certain problems faced

Bayesian models of perception : a tutorial introduction

Bayesian approaches to perception offer a principled, coherent and elegant answer to the central problem of perception: what the brain should believe about the world based on sensory data. This

Bayesian models of perceptual organization

One of the central ideas in the study of perception is that the proximal stimulus—the pattern of energy that impinges on sensory receptors, such as the visual image—is not sufficient to specify the

The Origin of Time In Conscious Agents

Studies of the evolution of perception using evolutionary games and genetic algorithms reveal that natural selection routinely drives veridical perceptions (i.e., perceptions that resemble the truth)

Inflections of the Bayesian Paradigm in Perceptual Psychology

It is maintained that, while there is homogeneity between Bayesian models of visual perception in their formal setup, remarkable differences can be found in their substantive aspect, that is, how the question “Where do probabilities come from?” is answered when designing the models.



Natural Selection and Shape Perception : Shape as an Effective Code for Fitness

Our perception of shape is, like all of our perceptions, a pro duct of evolution by natural selection. This entails that our perception of shap e is a satisficing solution to certain problems faced

Bayesian natural selection and the evolution of perceptual systems.

  • W. GeislerR. Diehl
  • Biology
    Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 2002
A formal framework for analysing how the statistics of natural stimuli and the process of natural selection interact to determine the design of perceptual systems is proposed and it is suggested that the Bayesian approach is appropriate not only for the study of perceptual Systems but also for theStudy of many other systems in biology.

Tuning Your Priors to the World

Tuning the prior to observed environmental frequencies is subject to overfitting, meaning in this context overtuning to the environment, which leads (ironically) to poor performance in future encounters with the same environment.

Perception viewed as an inverse problem

Natural selection and veridical perceptions.


This is a reprint of David Marr’s 1982 book. A foreword placing the book in its historical context is added by Shimon Ullman, and an afterword by Tomaso Poggio is added on some of the themes in the

Shape Perception in Human and Computer Vision: An Interdisciplinary Perspective

This comprehensive and authoritative text/reference presents a unique, multidisciplinary perspective on Shape Perception in Human and Computer Vision, with viewpoints from world-class researchers reflecting broadly on the issues that have shaped the field.

Bayesian color constancy.

  • D. BrainardW. Freeman
  • Mathematics
    Journal of the Optical Society of America. A, Optics, image science, and vision
  • 1997
A new estimator, which is called the maximum local mass (MLM) estimate, that integrates local probability density and uses an optimality criterion that is appropriate for perception tasks: It finds the most probable approximately correct answer.

Visual perception and the statistical properties of natural scenes.

  • W. Geisler
  • Psychology
    Annual review of psychology
  • 2008
This review begins with a general discussion of the natural scene statistics approach, of the different kinds of statistics that can be measured, and of some existing measurement techniques, followed by a summary of thenatural scene statistics measured over the past 20 years.