An Active Efficient Coding Model of Binocular Vision Development Under Normal and Abnormal Rearing Conditions

Klimmasch, Lukas; Schneider, Johann; Lelais, Alexander; Shi, Bertram E.; Triesch, Jochen

doi:10.1007/978-3-319-97628-0_6

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This bias is strongly shaped by the stimulus statistics the agent is facing during training, as there is a prevalence of horizontal and vertical edges. We have investigated RF properties which arise from normal and abnormal rearing conditions in more detail in Klimmasch et al (2018).…”

Section: Resultsmentioning

confidence: 99%

Autonomous Development of Active Binocular and Motion Vision Through Active Efficient Coding

et al. 2019

Self Cite

View full text Add to dashboard Cite

We present a model for the autonomous and simultaneous learning of active binocular and motion vision. The model is based on the Active Efficient Coding (AEC) framework, a recent generalization of classic efficient coding theories to active perception. The model learns how to efficiently encode the incoming visual signals generated by an object moving in 3-D through sparse coding. Simultaneously, it learns how to produce eye movements that further improve the efficiency of the sensory coding. This learning is driven by an intrinsic motivation to maximize the system's coding efficiency. We test our approach on the humanoid robot iCub using simulations. The model demonstrates self-calibration of accurate object fixation and tracking of moving objects. Our results show that the model keeps improving until it hits physical constraints such as camera or motor resolution, or limits on its internal coding capacity. Furthermore, we show that the emerging sensory tuning properties are in line with results on disparity, motion, and motion-in-depth tuning in the visual cortex of mammals. The model suggests that vergence and tracking eye movements can be viewed as fundamentally having the same objective of maximizing the coding efficiency of the visual system and that they can be learned and calibrated jointly through AEC.

show abstract

Section: Resultsmentioning

confidence: 99%