Binding representational spaces of colors and emotions for creativity

To implement cognitive functions such as creativity, the ability to create analogies and metaphors it is important to have mechanisms binding different representational spaces. The paper discusses this issue in the broader context of having a robot "artist", able to process his visual perception, to use his experience and skills as a painter, and to develop a creative digital artifact. In this context, two different spaces of color representation are respectively used to associate a linguistic label and an emotional value to color palettes. The robot, taking advantage of the proposed neural architecture, can decide which palette use depending on desired emotion to communicate through artifacts. The experience concerning palette-emotion association is derived from the analysis of data with textual description available on the web. The representation of colors and palettes is obtained using neural networks and via mechanisms of self association that creates the knowledge base to support the choice of the palette.