WaveGrad by @cnxhk et al is a clever new neural net for generating speech. It starts with random noise, and iteratively denoises, essentially hallucinating a voice in the noise. Listen to the voice emerge, as the number of iterations increases with time 🔉
the video shows mel-spectrogram features that are used to guide the denoising and specify the speech to produce. These could be the output of a text-to-speech system
give each pixel a random Pokemon type, and then battle pixels against their neighbors, updating each pixel with the winning type (using the Pokemon type chart)
we quickly see areas of fire > water > grass > fire, electric sweeping over, ground frontiers taking over etc etc
this is a cellular automaton, inspired by the rock-paper-scissors automaton-
no matter how chaotic and unstable the orbits of these three gravitational bodies are, their centre of gravity (centroid of the triangle) always remains stationary and fixed in space
in general the centre of gravity moves at a constant velocity, but I ensured this velocity was zero for these simulations