Watch neural networks see only what they've been trained to see

Memo Akten created Gloomy Sunday, part of his Learning To See series in which he juxtaposes mundane video with how deep-trained neural networks percieve the same input.

Via his site:

"Learning To See" is an ongoing series of works that use state-of-the-art Machine Learning algorithms as a means of reflecting on ourselves and how we make sense of the world.

The picture we see in our conscious minds is not a direct representation of the outside world, or of what our senses deliver, but is of a simulated world, reconstructed based on our expectations and prior beliefs. Artificial neural networks loosely inspired by our own visual cortex look through surveillance cameras and try to make sense of what they are seeing. Of course they can see only what they already know. Just like us.

The work is part of a broader line of inquiry about self affirming cognitive biases, our inability to see the world from others' point of view, and the resulting social polarisation.

And yes, that title is a reference to the Diamanda Galas cover of Billie Holiday:

gloomy sunday (Vimeo / Memo Akten)