Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
From MaRDI portal
Publication:3503734
DOI10.1162/neco.2008.04-07-510zbMath1140.68057OpenAlexW2064630666WikidataQ51894054 ScholiaQ51894054MaRDI QIDQ3503734
Nicolas Le Roux, Yoshua Bengio
Publication date: 9 June 2008
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.2008.04-07-510
Related Items
Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*, Minimal model of permutation symmetry in unsupervised learning, ‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space, Features Reweighting and Selection in ligand-based Virtual Screening for Molecular Similarity Searching Based on Deep Belief Networks, An implicitization challenge for binary factor analysis, Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models, Hierarchical models as marginals of hierarchical models, On the importance of hidden bias and hidden entropy in representational efficiency of the Gaussian-bipolar restricted Boltzmann machines, A new mechanical approach to handle generalized Hopfield neural networks, An adaptive deep Q-learning strategy for handwritten digit recognition, Dimension of Marginals of Kronecker Product Models, Two-layer contractive encodings for learning stable nonlinear features, Deep learning of support vector machines with class probability output networks, Representations of hypergraph states with neural networks*, Explicit demonstration of initial state construction in artificial neural networks using netket and IBM Q experience platform, Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints, Approximation Analysis of Convolutional Neural Networks, Unnamed Item, Training restricted Boltzmann machines: an introduction, \(p\)-adic statistical field theory and deep belief networks, Representations of graph states with neural networks, Neural network operations and Susuki–Trotter evolution of neural network states, Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units, Decreasing the Size of the Restricted Boltzmann Machine, Unifying neural-network quantum states and correlator product states via tensor networks, Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines, Storing, learning and retrieving biased patterns, Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks, Deep Belief Networks Are Compact Universal Approximators, Unnamed Item, Discriminative deep belief networks for visual data classification, The shape Boltzmann machine: a strong model of object shape, Modeling the Correlated Activity of Neural Populations: A Review, When Does a Mixture of Products Contain a Product of Mixtures?, Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit, Compact neural-network quantum state representations of Jastrow and stabilizer states, Functional clones and expressibility of partition functions
