The most fascinating thing about these programs is the undeniably imaginative, dreamlike nature of the output. Spend time actually using them and you will be continually surprised and engaged. Any human nuance you can interpret visually can be generated.
There is a high level of similarity with the mechanism human brains use to visualize things. This makes sense, because the neural networks are being trained to approximate that very function.
The output of these programs is not mimicry any more than the output of a human artist is. It's just more limited in the computational power available to the algorithm. The space of these generative expressions is vast, and significantly overlaps the space of art humans are able to produce.
Moore's law and algorithmic improvements will inevitably expand the capability of software to produce art to such an extent that all "human" capacities will be exceeded, for any and all metrics and nuances you can imagine.
There is a high level of similarity with the mechanism human brains use to visualize things. This makes sense, because the neural networks are being trained to approximate that very function.
The output of these programs is not mimicry any more than the output of a human artist is. It's just more limited in the computational power available to the algorithm. The space of these generative expressions is vast, and significantly overlaps the space of art humans are able to produce.
Moore's law and algorithmic improvements will inevitably expand the capability of software to produce art to such an extent that all "human" capacities will be exceeded, for any and all metrics and nuances you can imagine.