Efficient team structures in an open-ended cooperative creativity experiment

Sony CSL

Creativity is progressively acknowledged as the main driver for progress in all sectors of humankind’s activities: arts, science, technology, business, and social policies. Nowadays, many creative processes rely on many actors collectively contributing to an outcome. The same is true when groups of people collaborate in the solution of a complex problem. Despite the critical […]

Learning Complex Basis Functions For Invariant Representations Of Audio

Sony CSL

Learning features from data has shown to be more successful than using hand-crafted features for many machine learning tasks. Inmusicinformationretrieval(MIR), features learned from windowed spectrograms are highly variant to transformations like transposition or time-shift. Such variances are undesirable when they are irrelevant for the respective MIR task. We propose an architecture called Complex Autoencoder (CAE) […]

Monte Carlo Information-Geometric Structures

Sony CSL

Exponential families and mixture families are parametric probability models that can be geometrically studied as smooth statistical manifolds with respect to any statistical divergence like the Kullback–Leibler (KL) divergence or the Hellinger divergence. When equipping a statistical manifold with the KL divergence, the induced manifold structure is dually flat, and the KL divergence between distributions […]

NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpainting

Sony CSL

Inpainting-based generative modeling allows for stimulating human-machine interactions by letting users perform stylistically coherent local editions to an object using a statistical model. We presentNONOTO, a new interface for interactive music generation based on in-painting models. It is aimed both at researchers, by offering a simple and flexible API allowing them to connect their own […]