Neurokolloq: Prof. Jun Tani

Talk by Prof. Jun Tani (Okinawa Institute of Science and Technology) 

Title: Exploring Robotic Minds by Using the Predictive Coding Framework

When: September 26, 2018 at 04:00 pm

Where: Fenster der Wissenschaft (Floor 5), Charite Crossover, Virchowweg 6, 10117 Berlin

Host: Mototaka Suzuki (AG Larkum)

Abstarct:
My research motivation has been to investigate how cognitive agents can acquire structural representation via iterative interaction with the world, exercising agency and learning from resultant perceptual experience. Over the past 20 years, my group has tackled on this problem by investigating the idea of predictive coding applied to development of cognitive constructs of robots. Under the principle of predictive coding, dense interaction take place between the top-down intention proactively acting on the outer world and the resultant bottom-up perceptual reality accompanied with the prediction error. Our finding has been that compositionality enabling some conceptualization can emerge via such iterative interaction as the result of downward causation in terms of constraints such as multiple spatio-temporal scale property applied to the neural network modeling. The talk will highlight our recent results on interactive and integrative learning among multi-modality of perceptual channels including pixel level dynamic vision and proprioception using a humanoid robot platform. Finally, I will briefly discuss how we can bridge the gap between deterministic and probabilistic models in dealing with fluctuated spatio-temporal patterns by introducing a novel variational Bayes predictive coding scheme.

Reference:

(1) J. Tani: “Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-Organizing Dynamic Phenomena.”, Oxford University Press, 2016.