Description
Based on the research and development for Abstract Language Model — a machine created semiotic system which is based on all existing human signs, but transferred into and recreated with a machine-learned model — Semiotic Interpolations are the visual representations of selected models. By training all of the more than 65.000 characters included in the Unicode basic multilingual plane system with an artificial neural network, the variational autoencoder creates latent points where the most accurate representation of the characters is achieved. However, between these points interpolation becomes possible, which means that among two previously distinct characters now infinite characters come into existence, which can be seen as the origin of a transitionless, purely machine created semiotic system.
