Corpus ID: 11541755

Posterior distribution analysis for Bayesian inference in neural networks

@inproceedings{Myshkov2016PosteriorDA,
  title={Posterior distribution analysis for Bayesian inference in neural networks},
  author={Pavel Myshkov and S. Julier},
  year={2016}
}
  • Pavel Myshkov, S. Julier
  • Published 2016
  • This study explores the posterior predictive distributions obtained with various Bayesian inference methods for neural networks. The quality of the distributions is assessed both visually and quantitatively using Kullback–Leibler (KL) divergence, Kolmogorov–Smirnov (KS) distance and precision-recall scores. We perform the analysis using a synthetic dataset that allows for a more detailed examination of the methods, and validate the findings on larger datasets. We find that among the recently… CONTINUE READING
    16 Citations

    Figures and Tables from this paper.

    Quality of Uncertainty Quantification for Bayesian Neural Network Inference
    • 24
    • PDF
    Gradient conjugate priors and multi-layer neural networks
    • 3
    • PDF
    Gradient conjugate priors and deep neural networks
    • 1
    Pairing an arbitrary regressor with an artificial neural network estimating aleatoric uncertainty
    • 7
    Optimal deep neural networks by maximization of the approximation power
    • 1
    • Highly Influenced
    Inference Over Distribution of Posterior Class Probabilities for Reliable Bayesian Classification and Object-Level Perception
    • 3
    • Highly Influenced
    • PDF
    Estimation of Prediction Intervals in Neural Network-Based Regression Models
    • Kristian Miok
    • Computer Science
    • 2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)
    • 2018
    • 5
    Quantum-Inspired Hamiltonian Monte Carlo for Bayesian Sampling
    • 1
    • PDF
    Generating Data using Monte Carlo Dropout
    • 3
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 14 REFERENCES
    Bayesian Learning via Stochastic Gradient Langevin Dynamics
    • 1,123
    • Highly Influential
    • PDF
    Stochastic Backpropagation and Approximate Inference in Deep Generative Models
    • 2,844
    • PDF
    Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
    • 457
    • Highly Influential
    • PDF
    Bayesian learning for neural networks
    • 3,241
    • PDF
    Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
    • 2,426
    • Highly Influential
    • PDF
    Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
    • 156
    • PDF
    A family of algorithms for approximate Bayesian inference
    • 909
    • PDF
    Weight Uncertainty in Neural Networks
    • 888
    • Highly Influential
    • PDF
    Stochastic Gradient Hamiltonian Monte Carlo
    • 457
    • Highly Influential
    • PDF
    Dropout: a simple way to prevent neural networks from overfitting
    • 20,150
    • PDF