This paper explores the use of repeat-until-success circuits enabled by real-time control-flow feedback to realize quantum neurons with non-linear activation functions. These neurons are used to construct a minimal feedforward quantum neural network capable of learning all 2-to-1-bit Boolean functions. This model is shown to perform non-linear classification and effectively learns from multiple copies of a single training state consisting of the maximal superposition of all inputs. Variational quantum algorithms are also discussed as a promising implementation for parametrized quantum circuits.
