Hannu Töyrylä


The house that is no longer (2018) is balancing between the transformative and the generative, a typical characteristic of my neural art. Making art with neural networks is for me largely an extension of photography. My ultimate goal again might be described as if to simplify, to reduce images to the bare essentials.

 One of my favourite methods is to use one neural model to reduce photos to contours, looking like woolen threads, and then to use this reduced image as a virtual printing plate, in another neural model, to produce a virtual art print eventually to be printed on fine art paper. Depending on the training of the two models, often involving a healthy dose of overfitting, a range of different looks can be obtained. In another series, I have trained a model to apply a varying amount of virtual scratches to photos.

Finally, even though GANs are by far dominating the neural art at the moment, I have never totally abandoned the style transfer methods, but instead tried to extend and bend them to new directions, beyond mere style transfer.

I am a visual artist, based in Finland, with a background in both information technology and humanities research. I have been working on artistic applications of neural networks since 2015.