For instance, Yuille and Bülthoff [44] describe the Bayesian approach to perception in terms of faithful depiction: “We define vision as perceptual inference, the estimation of scene properties from an image or sequence of images . . . ther…44. Yuille, A., and Bülthoff, H. (1996). Bayesian decision theory and psychophysics, in Perception as Bayesian inference, ed. D. Knill and W. Richards (Cambridge University Press, Cambridge).
45. Zollman, K. (2005). Talking to neighbors: T…
Heinrich Bülthoff
scientist · 2 mentions across 1 reading
In this course
Bülthoff is a cognitive scientist known for modeling human perception through Bayesian inference, treating vision as probabilistic inference from incomplete sensory data rather than direct representation of the world. His work with Yuille is cited here to ground the course's engagement with how both biological and artificial systems estimate scene properties from images, bridging perception studies and computational approaches central to understanding machine learning's epistemological stakes. This framework matters for thinking through how AI vision systems might relate to human perceptual constraints and assumptions.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.