Multitasking associative networks

Abstract

We introduce a bipartite, diluted and frustrated, network as a sparse restricted Boltzman machine and we show its thermodynamical equivalence to an associative working memory able to retrieve multiple patterns in parallel without falling into spurious states typical of classical neural networks. We focus on systems processing in parallel a finite (up to logarithmic growth in the volume) amount of patterns, mirroring the low-level storage of standard Amit-Gutfreund-Sompolinsky theory. Results obtained trough statistical mechanics, signal-to-noise technique and Monte Carlo simulations are overall in perfect agreement and carry interesting biological insights. Indeed, these associative networks pave new perspectives in the understanding of multitasking features expressed by complex systems, e.g. neural and immune networks.

to appear on Phys.Rev.Lett

Cited by in corpus (64)

• Emergence of Compositional Representations in Restricted Boltzmann Machines
• Efficiency of attack strategies on complex model and real-world networks
• Regulation of Irregular Neuronal Firing by Autaptic Transmission
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Towards the development of human immune-system-on-a-chip platforms
• Frequency-difference-dependent stochastic resonance in neural systems
• Restricted Boltzmann Machine, recent advances and mean-field theory
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Phase transitions in Restricted Boltzmann Machines with generic priors
• Extensive load in multitasking associative networks
• Thermodynamics of Restricted Boltzmann Machines and related learning dynamics
• From Dyson to Hopfield: Processing on hierarchical networks
• Immune networks: multi-tasking capabilities near saturation
• Spectral Dynamics of Learning Restricted Boltzmann Machines
• Free energy and complexity of spherical bipartite models
• Universality in bipartite mean field spin glasses
• Non-Convex Multi-species Hopfield models
• Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses
• Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
• Dreaming neural networks: rigorous results
• Hierarchical neural networks perform both serial and parallel processing
• Statistical Physics and Representations in Real and Artificial Neural Networks
• Mean field bipartite spin models treated with mechanical techniques
• Parallel processing in immune networks
• Unsupervised feature learning from finite data by message passing: discontinuous versus continuous phase transition
• Barriers and Dynamical Paths in Alternating Gibbs Sampling of Restricted Boltzmann Machines
• Replica symmetry breaking in multi-species Sherrington-Kirkpatrick model
• Notes on stochastic (bio)-logic gates: the role of allosteric cooperativity
• A complete mean-field theory for dynamics of binary recurrent neural networks
• Meta-stable states in the hierarchical Dyson model drive parallel processing in the hierarchical Hopfield network
• Complete integrability of information processing by biochemical reactions
• Cluster analysis of weighted bipartite networks: a new copula-based approach
• Hopfield model with planted patterns: a teacher-student self-supervised learning model
• Parallel Learning by Multitasking Neural Networks
• Topological properties of hierarchical networks
• Free energies of Boltzmann Machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit
• Space of Functions Computed by Deep-Layered Machines
• Analogue neural networks on correlated random graphs
• Statistical-mechanical study of deep Boltzmann machine given weight parameters after training by singular value decomposition
• Dense Hopfield Networks in the Teacher-Student Setting
• PDE/statistical mechanics duality: relation between Guerra's interpolated $p$-spin ferromagnets and the Burgers hierarchy
• Role of zero synapses in unsupervised feature learning
• Another look at the Gardner problem
• A dynamical model of the adaptive immune system: effects of cells promiscuity, antigens and B-B interactions
• Optimized brute-force algorithms for the bifurcation analysis of a spin-glass-like neural network model
• The Relativistic Hopfield network: rigorous results
• Interpolating between boolean and extremely high noisy patterns through Minimal Dense Associative Memories
• Discrete perceptrons
• Vitality of Neural Networks under Reoccurring Catastrophic Failures
• Associative networks with diluted patterns: dynamical analysis at low and medium load
• Spherical perceptron as a storage memory with limited errors
• The relativistic Hopfield model with correlated patterns
• Regular graphs maximize the variability of random neural networks
• A relativistic extension of Hopfield neural networks via the mechanical analogy
• Negative spherical perceptron
• Anergy in self-directed B lymphocytes from a statistical mechanics perspective
• Overcoming the complexity barrier of the dynamic message-passing method in networks with fat-tailed degree distributions
• Uncovering the non-equilibrium stationary properties in sparse Boolean networks
• Dynamical prediction of two meteorological factors using the deep neural network and the long short term memory $(1)$
• Dilution of Ferromagnets via a Random Graph-based Strategy
• Multitasking network with fast noise
• Ferromagnetic models for cooperative behavior: Revisiting Universality in complex phenomena
• Parallel retrieval of correlated patterns
• Exact training of Restricted Boltzmann machines on intrinsically low dimensional data