| Popis: |
The recent advances in the application of artificial neural networks in the biological field have been inspired by the functional organization of real biological structures (Draye et al.,1997a; Anastasio & Gad, 2007). The fascination exerted by the oculomotor system upon both engineers and neuroscientists have played an important role in this issue. In particular, since the definitive evidence of the existence of a neural integrator in the brainstem (Cheron et al., 1986a; Cannon & Robinson, 1987; Robinson, 1989 for a review) performing mathematical integration of the eye velocity into eye position signals, numerous artificial networks have been developed allowing a better understanding of the fundamental question of how the brain control movement. Such bio-mimetic strategy has recently permitted to elaborate different dynamic recurrent neural networks (DRNN) specifically dedicated to the command of humanoid robot (Tani et al., 2008). Hierarchical neuralinspired modules have also been proposed forming cascades of forward dynamics models (Jordan & Rumelhart, 1992; Kawato et al., 1987; Tani, 2003) in which top-down and bottomup influences allowed generating behavioural primitives. This Chapter describes the main steps performed in the development of our DRNN from the neural integrator models to those applied in the field of human movement control. |
