Classical and superposed learning for quantum weightless neural networks

摘要: A supervised learning algorithm for quantum neural networks (QNN) based on a novel neuron node implemented as very simple circuit is proposed and investigated. In contrast to the QNN published in literature, model can perform both simulate classical models. This partly due used elsewhere which has weights non-linear activations functions. Here weightless network quantisation of (WNN). The theoretical practical results WNN be inherited by these (qWNN). here patterns training set are presented concurrently superposition. superposition-based (SLA) computational cost polynomial number set.