Corpus ID: 118318349

Learning hyperparameters for neural network models using Hamiltonian dynamics

@inproceedings{Choo2000LearningHF,
  title={Learning hyperparameters for neural network models using Hamiltonian dynamics},
  author={Kiam Choo},
  year={2000}
}
  • Kiam Choo
  • Published 2000
  • Mathematics
  • Learning Hyperparameters for Neural Network Models Using Hamiltonian Dynamics Kiam Choo Master of Science Graduate Department of Computer Science University of Toronto 2000 We consider a feedforward neural network model with hyperparameters controlling groups of weights. Given some training data, the posterior distribution of the weights and the hyperparameters can be obtained by alternately updating the weights with hybrid Monte Carlo and sampling from the hyperparameters using Gibbs sampling… CONTINUE READING
    14 Citations

    Figures from this paper

    Semi-Separable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models
    • PDF
    Semi-Separable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models
    • 18
    • PDF
    High Dimensional Markov Chain Monte Carlo with Multiple GPUs
    • PDF
    Fast hierarchical Gaussian processes
    • 14
    • PDF
    Slice sampling covariance hyperparameters of latent Gaussian models
    • 184
    • PDF
    MCMC Using Hamiltonian Dynamics
    • 1,773
    • PDF
    5 MCMC Using Hamiltonian Dynamics
    • 42
    • PDF

    References

    SHOWING 1-10 OF 14 REFERENCES
    Comparison of Approximate Methods for Handling Hyperparameters
    • D. MacKay
    • Computer Science, Mathematics
    • Neural Computation
    • 1999
    • 276
    • PDF
    Bayesian learning for neural networks
    • 3,348
    • Highly Influential
    • PDF
    Issues in Bayesian Analysis of Neural Network Models
    • 133
    • PDF
    Bayesian Back-Propagation
    • 349
    • PDF
    Neural Networks for Pattern Recognition
    • 13,998
    Non-Uniform Random Variate Generation
    • 3,491
    • Highly Influential
    • PDF
    Hybrid Monte Carlo
    • 2,038
    An Introduction To Probability Theory And Its Applications
    • 10,731
    • PDF
    Equation of state calculations by fast computing machines
    • 30,278
    • Highly Influential
    • PDF