This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
This paper contributes tothe study of nonlinear dynamical systems from a computational perspective. These systems are inherently more powerful than their linear counterparts (such...
Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth ...
Generalized linear models are the most commonly used tools to describe the stimulus selectivity of sensory neurons. Here we present a Bayesian treatment of such models. Using the ...
Sebastian Gerwinn, Jakob Macke, Matthias Seeger, M...
Visual inspection of neurons suggests that dendritic orientation may be determined both by internal constraints (e.g. membrane tension) and by external vector fields (e.g. neurotr...