Abstract:Autoencoding is a machine-learning technique for extracting a compact representation of the essential features of input data; this representation then enables a variety of applications that rely on encoding and subsequent reconstruction based on decoding of the relevant data. Here, we document our discovery that the biosphere evolves by a natural process akin to computer autoencoding. We establish the following points: (1) A species is defined by its species interaction code. The species code consists of the fundamental, core interactions of the species with its external and internal environments; core interactions are encoded by multi-scale networks including molecules-cells-organisms. (2) Evolution expresses sustainable changes in species interaction codes; these changing codes both map and construct the species environment. The survival of species is computed by what we term \textit{natural autoencoding}: arrays of input interactions generate species codes, which survive by decoding into sustained ecosystem interactions. This group process, termed survival-of-the-fitted, supplants the Darwinian struggle of individuals and survival-of-the-fittest only. DNA is only one element in natural autoencoding. (3) Natural autoencoding and artificial autoencoding techniques manifest defined similarities and differences. Biosphere autoencoding and survival-of-the-fitted sheds a new light on the mechanism of evolution. Evolutionary autoencoding renders evolution amenable to new approaches to computer modeling.