The role of coherence theory in attractor quantum neural networks
arXiv:2112.10867 · doi:10.22331/q-2022-09-08-794
Abstract
We investigate attractor quantum neural networks (aQNNs) within the framework of coherence theory. We show that: i) aQNNs are associated to non-coherence-generating quantum channels; ii) the depth of the network is given by the decohering power of the corresponding quantum map; and iii) the attractor associated to an arbitrary input state is the one minimizing their relative entropy. Further, we examine faulty aQNNs described by noisy quantum channels, derive their physical implementation and analyze under which conditions their performance can be enhanced by using entanglement or coherence as external resources.
References in corpus (18)
- Quantifying Coherence
- Machine learning and the physical sciences
- Operational Resource Theory of Coherence
- The quest for a Quantum Neural Network
- Robustness of coherence: An operational and observable measure of quantum coherence
- A rigorous and robust quantum speed-up in supervised machine learning
- Demonstration of quantum advantage in machine learning
- Quantum Hopfield neural network
- Quantifying Superposition
- Cohering and de-cohering power of quantum channels
- Resource Destroying Maps
- Genuine quantum coherence
- Quantum Neuron: an elementary building block for machine learning on quantum computers
- Maximally coherent states and coherence-preserving operations
- Using and reusing coherence to realize quantum processes
- Creating and destroying coherence with quantum channels
- Interpreting quantum coherence through a quantum measurement process
- A note on cohering power and de-cohering power