Adaptive learning in random linear nanoscale networks

While the top-down engineered CMOS technology favors regular and locally interconnected structures, emerging molecular and nanoscale bottom-up self-assembled devices will be built from vast numbers of simple, densely arranged components that exhibit high failure rates, are relatively slow, and connected in a disordered way. Such systems are not programmable by standard means. Here we provide a solution to the supervised learning problem of mapping a desired binary input to a desired binary output in an random nanoscale network of linear functions with given control nodes. The network model is inspired after self-assembled silver nanowires. Our results show that one- and two-control node random networks can implement linearly separable sets.