Dancing with deep learning
Gisela Arnal Romero · UPCommons institutional repository (Universitat Politècnica de Catalunya) · 2017
Art and technology are in constant synergetic expansion. Willy Barleycorn - Machine Learning in Dance. When art uses technology as a way of creation by the hand of the own artist it comes a synergy with great potential. “Dancing With Deep Learning” is born from the convergence between technology and art in order to create a machine-human collaboration. In such a manner, the system is a catalyst of inspiration for the dancer and choreographer, allowing them to expand their creations inside the artistic area. This fi- nal degree thesis exposes a generation system of new choreographic material in the own style of the dancer as a way to record her artistic repertory or proposing new material in front of the artistic lack. Inside of the core of ”Dancing with Deep Learning” we find a Recurrent Neural Network trained with given data by the movement of the dancer that is also capable of generating new sequences of dance.