Amorphous Solid Model of Vectorial Hopfield Neural Networks

• URL: http://arxiv.org/abs/2507.22787v1
• Date: Wed, 30 Jul 2025 15:51:54 GMT
• Title: Amorphous Solid Model of Vectorial Hopfield Neural Networks
• Authors: F. Gallavotti, A. Zaccone,
• Abstract summary: We present a vectorial extension of the Hopfield associative memory model inspired by the theory of amorphous solids.<n>The generalized Hebbian learning rule creates a block-structured weight matrix through outer products of stored pattern vectors.<n>We show that this model exhibits quantifiable structural properties characteristic of disordered materials.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a vectorial extension of the Hopfield associative memory model inspired by the theory of amorphous solids, where binary neural states are replaced by unit vectors $\mathbf{s}_i \in \mathbb{R}^3$ on the sphere $S^2$. The generalized Hebbian learning rule creates a block-structured weight matrix through outer products of stored pattern vectors, analogous to the Hessian matrix structure in amorphous solids. We demonstrate that this model exhibits quantifiable structural properties characteristic of disordered materials: energy landscapes with deep minima for stored patterns versus random configurations (energy gaps $\sim 7$ units), strongly anisotropic correlations encoded in the weight matrix (anisotropy ratios $\sim 10^2$), and order-disorder transitions controlled by the pattern density $\gamma = P/(N \cdot d)$. The enhanced memory capacity ($\gamma_c \approx 0.55$ for a fully-connected network) compared to binary networks ($\gamma_c \approx 0.138$) and the emergence of orientational correlations establish connections between associative memory mechanisms and amorphous solid physics, particularly in systems with continuous orientational degrees of freedom. We also unveil the scaling with the coordination number $Z$ of the memory capacity: $\gamma_c \sim (Z-6)$ from the isostatic point $Z_c =6$ of the 3D elastic network, which closely mirrors the scaling of the shear modulus $G \sim (Z-6)$ in 3D central-force spring networks.

Related papers

• Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computations [63.945006006152035]
  tensor decomposition networks (TDNs) achieve competitive performance with dramatic speedup in computations.<n>We evaluate TDNs on PubChemQCR, a newly curated molecular relaxation dataset containing 105 million DFT-calculated snapshots.
  arXiv  Detail & Related papers  (2025-07-01T18:46:27Z)
• Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches [0.0]
  We show that a convex function can be described with a second-order and symmetric function.<n>The ability of the model to capture arbitrary materials is demonstrated using synthetic and experimental data.
  arXiv  Detail & Related papers  (2025-03-01T17:55:09Z)
• Bridging conformal field theory and parton approaches to SU(n)_k chiral spin liquids [48.225436651971805]
  We employ the $mathrmSU(n)_k$ Wess-Zumino-Witten (WZW) model in conformal field theory to construct lattice wave functions in both one and two dimensions.<n>The spins on all lattice sites are chosen to transform under the $mathrmSU(n)$ irreducible representation with a single row and $k$ boxes in the Young tableau.
  arXiv  Detail & Related papers  (2025-01-16T14:42:00Z)
• High-Rank Irreducible Cartesian Tensor Decomposition and Bases of Equivariant Spaces [47.83974626445763]
  We construct path matrices for decomposition of Cartesian tensors up to rank $n=9$ with reduced and affordable complexity.<n>We prove and leverage that the concatenation of path matrices is an orthonormal change-of-basis matrix between the tensor product space and the spherical direct sum spaces.<n>We extend our result to the arbitrary tensor product and direct sum spaces, enabling free design between different spaces while keeping symmetry.
  arXiv  Detail & Related papers  (2024-12-24T08:25:38Z)
• Bose-Hubbard model with power-law hopping in one dimension [0.0]
  We investigate the one-dimensional Bose-Hubbard model with power-law hopping decaying with distance as $1/ralpha$.<n>For all $1alphaleq 3$ the quantum phase transition from a superfluid and a Mott at unit filling is found to be continuous and scale invariant.
  arXiv  Detail & Related papers  (2024-12-02T14:54:53Z)
• Entanglement renormalization of fractonic anisotropic $\mathbb{Z}_N$ Laplacian models [4.68169911641046]
  Gapped fracton phases constitute a new class of quantum states of matter which connects to topological orders but does not fit easily into existing paradigms.<n>We investigate the anisotropic $mathbbZ_N$ Laplacian model which can describe a family of fracton phases defined on arbitrary graphs.
  arXiv  Detail & Related papers  (2024-09-26T18:36:23Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Geometry of degenerate quantum states, configurations of $m$-planes and invariants on complex Grassmannians [55.2480439325792]
  We show how to reduce the geometry of degenerate states to the non-abelian connection $A$. We find independent invariants associated with each triple of subspaces. Some of them generalize the Berry-Pancharatnam phase, and some do not have analogues for 1-dimensional subspaces.
  arXiv  Detail & Related papers  (2024-04-04T06:39:28Z)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation [54.951832422425454]
  We introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3mathrmD$ rigid motions. Our family of FoldFlowgenerative models offers several advantages over previous approaches to the generative modeling of proteins.
  arXiv  Detail & Related papers  (2023-10-03T19:24:24Z)
• Tensor network simulation of the (1+1)-dimensional $O(3)$ nonlinear $\sigma$-model with $\theta=\pi$ term [17.494746371461694]
  We perform a tensor network simulation of the (1+1)-dimensional $O(3)$ nonlinear $sigma$-model with $theta=pi$ term. Within the Hamiltonian formulation, this field theory emerges as the finite-temperature partition function of a modified quantum rotor model decorated with magnetic monopoles.
  arXiv  Detail & Related papers  (2021-09-23T12:17:31Z)
• Dynamical Signatures of Chaos to Integrability Crossover in $2\ imes 2$ Generalized Random Matrix Ensembles [0.0]
  We study the energy correlations by calculating the density and 2nd moment of the Nearest Neighbor Spacing (NNS) We observe that for large $N$ the 2nd moment of NNS and the relative depth of the correlation hole exhibit a second order phase transition at $gamma=2$.
  arXiv  Detail & Related papers  (2020-10-28T05:02:13Z)

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.