Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

By Jun Tani. 2003

171 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Control and Systems Engineering, Social Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. German Ignacio Parisi
2. Stefan Wermter
3. Cornelius Weber
4. Olivier Sigaud
5. Alain Droniou
6. Jun Tani

In Control and Systems Engineering

1. German Ignacio Parisi
2. Stefan Wermter
3. Alain Droniou
4. Olivier Sigaud
5. Jun Tani
6. Cornelius Weber

In Social Psychology

1. German Ignacio Parisi
2. Alain Droniou
3. Olivier Sigaud
4. Stefan Wermter
5. Jun Tani
6. Cornelius Weber

Citations in the corpus

• Lifelong learning of human actions with deep neural network self-organization (2017, background): “Tani (2003) and Tani and Nolfi (1999) proposed that sensory-motor patterns for on-line planning in a robot learning scenario can be generated and recognized by using recurrent neural network models trained through prediction error minimization.”
• Towards Deep Developmental Learning (2016, background): “To approach the temporal clustering issue, one can consider that, when what happens immediately next is predictable, there some internal coherence into the temporal data, so it pertains to the same temporal unit [111], [112].”
• A Hierarchy of Time-Scales and the Brain (2008, unknown): “This is an important result, that is shared with several accounts in the robotics literature, where a hierarchy of time-scales in recurrent networks emerges naturally from optimizing a robot to perform navigation tasks [21,22,64,65].”
• Action understanding and active inference (2011, unknown): “ian (free-energy) perspective on the connectionist scheme introduced by Tani (2003) ; see also Tani et al. (2004) and Weber et al. (2006).”