Thermodynamics of bidirectional associative memories
- URL: http://arxiv.org/abs/2211.09694v2
- Date: Mon, 27 Mar 2023 14:27:57 GMT
- Title: Thermodynamics of bidirectional associative memories
- Authors: Adriano Barra, Giovanni Catania, Aur\'elien Decelle, Beatriz Seoane
- Abstract summary: We investigate the equilibrium properties of bidirectional associative memories (BAMs)
introduced by Kosko in 1988 as a generalization of the Hopfield model to a bipartite structure.
We characterize the computational capabilities of a extension of this model in the thermodynamic limit.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: In this paper we investigate the equilibrium properties of bidirectional
associative memories (BAMs). Introduced by Kosko in 1988 as a generalization of
the Hopfield model to a bipartite structure, the simplest architecture is
defined by two layers of neurons, with synaptic connections only between units
of different layers: even without internal connections within each layer,
information storage and retrieval are still possible through the reverberation
of neural activities passing from one layer to another. We characterize the
computational capabilities of a stochastic extension of this model in the
thermodynamic limit, by applying rigorous techniques from statistical physics.
A detailed picture of the phase diagram at the replica symmetric level is
provided, both at finite temperature and in the noiseless regimes. Also for the
latter, the critical load is further investigated up to one step of replica
symmetry breaking. An analytical and numerical inspection of the transition
curves (namely critical lines splitting the various modes of operation of the
machine) is carried out as the control parameters - noise, load and asymmetry
between the two layer sizes - are tuned. In particular, with a finite asymmetry
between the two layers, it is shown how the BAM can store information more
efficiently than the Hopfield model by requiring less parameters to encode a
fixed number of patterns. Comparisons are made with numerical simulations of
neural dynamics. Finally, a low-load analysis is carried out to explain the
retrieval mechanism in the BAM by analogy with two interacting Hopfield models.
A potential equivalence with two coupled Restricted Boltmzann Machines is also
discussed.
Related papers
- Duality between string and computational order in symmetry-enriched topological phases [0.0]
We present the first examples of topological phases of matter with uniform power for measurement-based quantum computation.
We show that ground states of the toric code in an anisotropic magnetic field yield a natural, albeit non-computationally-universal, application of our framework.
arXiv Detail & Related papers (2024-10-03T17:38:03Z) - Entanglement and the density matrix renormalisation group in the generalised Landau paradigm [0.0]
We leverage the interplay between gapped phases and dualities of symmetric one-dimensional quantum lattice models.
For every phase in the phase diagram, the dual representation of the ground state that breaks all symmetries minimises both the entanglement entropy and the required number of variational parameters.
Our work testifies to the usefulness of generalised non-invertible symmetries and their formal category theoretic description for the nuts and bolts simulation of strongly correlated systems.
arXiv Detail & Related papers (2024-08-12T17:51:00Z) - Exotic Symmetry Breaking Properties of Self-Dual Fracton Spin Models [4.467896011825295]
We investigate the ground-state properties and phase transitions of two self-dual fracton spin models.
We show that both models experience a strong first-order phase transition with an anomalous $L-(D-1)$ scaling.
Our work provides new understanding of sub-dimensional symmetry breaking and makes an important step for studying quantum-error-correction properties of the checkerboard and Haah's codes.
arXiv Detail & Related papers (2023-11-18T13:12:14Z) - Synthetic $\mathbb{Z}_2$ gauge theories based on parametric excitations
of trapped ions [0.0]
We present a detailed scheme for the analog quantum simulation of Z2 gauge theories in crystals of trapped ions.
We introduce a versatile toolbox based on parametric excitations corresponding to different spin-motion-coupling schemes.
This building block, when implemented with a single trapped ion, corresponds to a minimal Z2 gauge theory.
arXiv Detail & Related papers (2023-05-15T15:01:09Z) - Capturing dynamical correlations using implicit neural representations [85.66456606776552]
We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data.
In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
arXiv Detail & Related papers (2023-04-08T07:55:36Z) - Modeling the space-time correlation of pulsed twin beams [68.8204255655161]
Entangled twin-beams generated by parametric down-conversion are among the favorite sources for imaging-oriented applications.
We propose a semi-analytic model which aims to bridge the gap between time-consuming numerical simulations and the unrealistic plane-wave pump theory.
arXiv Detail & Related papers (2023-01-18T11:29:49Z) - Quantum correlations, entanglement spectrum and coherence of
two-particle reduced density matrix in the Extended Hubbard Model [62.997667081978825]
We study the ground state properties of the one-dimensional extended Hubbard model at half-filling.
In particular, in the superconducting region, we obtain that the entanglement spectrum signals a transition between a dominant singlet (SS) to triplet (TS) pairing ordering in the system.
arXiv Detail & Related papers (2021-10-29T21:02:24Z) - Memory kernel and divisibility of Gaussian Collisional Models [0.0]
Memory effects in the dynamics of open systems have been the subject of significant interest in the last decades.
We analyze two types of interactions, a beam-splitter implementing a partial SWAP and a two-mode squeezing, which entangles the ancillas and feeds excitations into the system.
By analyzing the memory kernel and divisibility for these two representative scenarios, our results help to shed light on the intricate mechanisms behind memory effects in the quantum domain.
arXiv Detail & Related papers (2020-08-03T10:28:55Z) - Provably Efficient Neural Estimation of Structural Equation Model: An
Adversarial Approach [144.21892195917758]
We study estimation in a class of generalized Structural equation models (SEMs)
We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent.
For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
arXiv Detail & Related papers (2020-07-02T17:55:47Z) - Dynamical solitons and boson fractionalization in cold-atom topological
insulators [110.83289076967895]
We study the $mathbbZ$ Bose-Hubbard model at incommensurate densities.
We show how defects in the $mathbbZ$ field can appear in the ground state, connecting different sectors.
Using a pumping argument, we show that it survives also for finite interactions.
arXiv Detail & Related papers (2020-03-24T17:31:34Z) - Inverse Learning of Symmetries [71.62109774068064]
We learn the symmetry transformation with a model consisting of two latent subspaces.
Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser.
Our model outperforms state-of-the-art methods on artificial and molecular datasets.
arXiv Detail & Related papers (2020-02-07T13:48:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.