An Efficient Learning Procedure for Deep Boltzmann Machines
From MaRDI portal
Publication:2919431
DOI10.1162/NECO_a_00311zbMath1247.68223OpenAlexW2071709160WikidataQ46424819 ScholiaQ46424819MaRDI QIDQ2919431
Ruslan R. Salakhutdinov, Geoffrey E. Hinton
Publication date: 2 October 2012
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco_a_00311
Learning and adaptive systems in artificial intelligence (68T05) Graphical methods in statistics (62A09)
Related Items (44)
Noise contrastive estimation: asymptotic properties, formal comparison with MC-MLE ⋮ Active inference on discrete state-spaces: a synthesis ⋮ Part-of-math tagging and applications ⋮ On better training the infinite restricted Boltzmann machines ⋮ Deterministic replica-exchange method without pseudo random numbers for simulations of complex systems ⋮ Lower bounds for testing graphical models: colorings and antiferromagnetic Ising models ⋮ Parallel computing of Edwards–Anderson model ⋮ Neural networks retrieving Boolean patterns in a sea of Gaussian ones ⋮ Two-layer contractive encodings for learning stable nonlinear features ⋮ Adversarial concept drift detection under poisoning attacks for robust data stream mining ⋮ Statistical Inference, Learning and Models in Big Data ⋮ Discriminative group-sparsity constrained broad learning system for visual recognition ⋮ Two-point step size gradient method for solving a deep learning problem ⋮ Minimax formula for the replica symmetric free energy of deep restricted Boltzmann machines ⋮ Deep learning for natural language processing: a survey ⋮ Geometric deep learning: a temperature based analysis of graph neural networks ⋮ Cauchy regularized broad learning system for noisy data regression ⋮ Spike-Timing-Dependent Construction ⋮ Timescale Separation in Recurrent Neural Networks ⋮ Deep Restricted Kernel Machines Using Conjugate Feature Duality ⋮ Quantum science and quantum technology ⋮ Analyzing market baskets by restricted Boltzmann machines ⋮ Modeling documents with Event Model ⋮ Visualizing and understanding sum-product networks ⋮ Decreasing the Size of the Restricted Boltzmann Machine ⋮ Adaptive Learning Algorithm Convergence in Passive and Reactive Environments ⋮ Thermodynamics of restricted Boltzmann machines and related learning dynamics ⋮ Unnamed Item ⋮ The Poisson transform for unnormalised statistical models ⋮ A selective overview of deep learning ⋮ Deep neural mapping support vector machines ⋮ Deep Boltzmann machines: rigorous results at arbitrary depth ⋮ The shape Boltzmann machine: a strong model of object shape ⋮ GADE: a generative adversarial approach to density estimation and its applications ⋮ A comprehensive survey and analysis of generative models in machine learning ⋮ Learning algorithm of Boltzmann machine based on spatial Monte Carlo integration method ⋮ A tale of three probabilistic families: Discriminative, descriptive, and generative models ⋮ A Generalization of Spatial Monte Carlo Integration ⋮ Legendre decomposition for tensors* ⋮ Enhancing performance of the back-propagation algorithm based on a novel regularization method of preserving inter-object-distance of data ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Belief propagation as diffusion ⋮ On the thermodynamic interpretation of deep learning systems
Cites Work
- Optimization by Simulated Annealing
- Parametric inference for imperfectly observed Gibbsian fields
- Connectionist learning of belief networks
- Reducing the Dimensionality of Data with Neural Networks
- Training Products of Experts by Minimizing Contrastive Divergence
- Learning Deep Architectures for AI
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
- A Fast Learning Algorithm for Deep Belief Nets
- A Stochastic Approximation Method
- Training invariant support vector machines
This page was built for publication: An Efficient Learning Procedure for Deep Boltzmann Machines
