Trainability of Dissipative Perceptron-Based Quantum Neural Networks. (arXiv:2005.12458v2 [quant-ph] UPDATED)

Several architectures have been proposed for quantum neural networks (QNNs),
with the goal of efficiently performing machine learning tasks on quantum data.
Rigorous scaling results are urgently needed for specific QNN constructions to
understand which, if any, will be trainable at a large scale. Here, we analyze
the gradient scaling (and hence the trainability) for a recently proposed
architecture that we called dissipative QNNs (DQNNs), where the input qubits of
each layer are discarded at the layer's output. We find …

arxiv networks neural networks perceptron quantum quantum neural networks