THE GENERATION OF ANIMATED MOTION BY MEANS OF A RECURRENT NEURAL-NETWORK

The possibility to use neural networks to guide animated motion sequen ces is investigated. The performance of two recurrent architectures, b oth derived from the cascade-correlation network, is compared. These a rchitectures only differ in the objective function used to train the h idden units. Small differences in performance were observed, but both networks could successfully produce simple motion sequences. An animat ion environment was created to display arm movement and walking sequen ces.