Optimal storage capacity of quantum Hopfield neural networks

Abstract

Quantum neural networks form one pillar of the emergent field of quantum machine learning. Here, quantum generalisations of classical networks realizing associative memories - capable of retrieving patterns, or memories, from corrupted initial states - have been proposed. It is a challenging open problem to analyze quantum associative memories with an extensive number of patterns, and to determine the maximal number of patterns the quantum networks can reliably store, i.e. their storage capacity. In this work, we propose and explore a general method for evaluating the maximal storage capacity of quantum neural network models. By generalizing what is known as Gardner's approach in the classical realm, we exploit the theory of classical spin glasses for deriving the optimal storage capacity of quantum networks with quenched pattern variables. As an example, we apply our method to an open-system quantum associative memory formed of interacting spin-1/2 particles realizing coupled artificial neurons. The system undergoes a Markovian time evolution resulting from a dissipative retrieval dynamics that competes with a coherent quantum dynamics. We map out the non-equilibrium phase diagram and study the effect of temperature and Hamiltonian dynamics on the storage capacity. Our method opens an avenue for a systematic characterization of the storage capacity of quantum associative memories.

6 pages, 2 figures + appendix

References in corpus (9)

• The quest for a Quantum Neural Network
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Quantum computing models for artificial neural networks
• Trapped Ion Chain as a Neural Network: Error Resistant Quantum Computation
• Replica Symmetry Breaking in Cold Atoms and Spin Glasses
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• A Quantum Hopfield Associative Memory Implemented on an Actual Quantum Processor
• Self-induced glassy phase in multimodal cavity quantum electrodynamics
• Pattern capacity of a single quantum perceptron

Cited by in corpus (6)

• Long-range interacting systems are locally non-interacting
• Quantum memories for squeezed and coherent superpositions in a driven-dissipative nonlinear oscillator
• Dissipative quantum many-body dynamics in (1+1)D quantum cellular automata and quantum neural networks
• Dissipative Quantum Hopfield Network: A numerical analysis
• Non-linear classification capability of quantum neural networks due to emergent quantum metastability
• Neural networks with quantum states of light