Open quantum generalisation of Hopfield neural networks

Abstract

We propose a new framework to understand how quantum effects may impact on the dynamics of neural networks. We implement the dynamics of neural networks in terms of Markovian open quantum systems, which allows us to treat thermal and quantum coherent effects on the same footing. In particular, we propose an open quantum generalisation of the celebrated Hopfield neural network, the simplest toy model of associative memory. We determine its phase diagram and show that quantum fluctuations give rise to a qualitatively new non-equilibrium phase. This novel phase is characterised by limit cycles corresponding to high-dimensional stationary manifolds that may be regarded as a generalisation of storage patterns to the quantum domain.

References in corpus (4)

• The quest for a Quantum Neural Network
• Coherent quantum dynamics in steady-state manifolds of strongly dissipative systems
• Limit cycle phase in driven-dissipative spin systems
• Temperature scaling law for quantum annealing optimizers

Cited by in corpus (35)

• Continuous-variable quantum neural networks
• Open quantum systems with local and collective incoherent processes: Efficient numerical simulation using permutational invariance
• Is quantum advantage the right goal for quantum machine learning?
• Quantum Hopfield neural network
• Spinor self-ordering of a quantum gas in a cavity
• Sign-changing photon-mediated atom interactions in multimode cavity QED
• Exactness of mean-field equations for open Dicke models with an application to pattern retrieval dynamics
• Atom-only descriptions of the driven-dissipative Dicke model
• Enhancing associative memory recall and storage capacity using confocal cavity QED
• Entanglement and replica symmetry breaking in a driven-dissipative quantum spin glass
• A high-cooperativity confocal cavity QED microscope
• The effect of active photons on dynamical frustration in cavity QED
• Rapid training of quantum recurrent neural networks
• Quantum associative memory with a single driven-dissipative nonlinear oscillator
• Mean-field dynamics of open quantum systems with collective operator-valued rates: validity and application
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• Long-range interacting systems are locally non-interacting
• Optimal storage capacity of quantum Hopfield neural networks
• Quantum accelerated approach to the thermal state of classical spin systems with applications to pattern-retrieval in the Hopfield neural network
• Quantum memories for squeezed and coherent superpositions in a driven-dissipative nonlinear oscillator
• Designing ground states of Hopfield networks for quantum state preparation
• Self-induced glassy phase in multimodal cavity quantum electrodynamics
• A quantum algorithm for track reconstruction in the LHCb vertex detector
• Classifying quantum data by dissipation
• A model of interacting quantum neurons with a dynamic synapse
• Dissipative quantum many-body dynamics in (1+1)D quantum cellular automata and quantum neural networks
• Can biological quantum networks solve NP-hard problems?
• Dissipative Quantum Hopfield Network: A numerical analysis
• Dynamics of strongly coupled disordered dissipative spin-boson systems
• Non-linear classification capability of quantum neural networks due to emergent quantum metastability
• Unitary Evolutions Sourced By Interacting Quantum Memories: Closed Quantum Systems Directing Themselves Using Their State Histories
• Non-stationarity and Dissipative Time Crystals: Spectral Properties and Finite-Size Effects
• Quantum Hopfield Model with Dilute Memories
• Nonergodic delocalized paramagnetic states in quantum neural networks
• Macroscopic theory of multipartite correlations in permutation-invariant open quantum systems