Weightless neural network parameters and architecture selection in a quantum computer
This work addresses the challenge of automating architecture selection for quantum neural networks, which is incremental as it builds on existing techniques for classical networks.
The paper tackles the problem of tedious empirical evaluation for neural network architecture selection by proposing a method for parameter and architecture selection in quantum weightless neural networks (qWNNs), using quantum superposition and a non-linear operator to perform a global search in the architecture and parameter space.
Training artificial neural networks requires a tedious empirical evaluation to determine a suitable neural network architecture. To avoid this empirical process several techniques have been proposed to automatise the architecture selection process. In this paper, we propose a method to perform parameter and architecture selection for a quantum weightless neural network (qWNN). The architecture selection is performed through the learning procedure of a qWNN with a learning algorithm that uses the principle of quantum superposition and a non-linear quantum operator. The main advantage of the proposed method is that it performs a global search in the space of qWNN architecture and parameters rather than a local search.