TOP-DOWN FEEDBACK IN AN HMAX-LIKE CORTICAL MODEL OF OBJECT PERCEPTION BASED ON HIERARCHICAL BAYESIAN NETWORKS AND BELIEF PROPAGATION.

Top-down feedback in an HMAX-like cortical model of object perception based on hierarchical Bayesian networks and belief propagation.

Hierarchical generative models, such as Bayesian networks, and belief propagation have been shown to provide a theoretical framework that can account for perceptual processes, including feedforward recognition and feedback modulation.The framework explains both psychophysical and physiological experimental data and maps well onto the hierarchical d

read more