Pith. sign in

REVIEW 7 cited by

Bayesian Recurrent Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1704.02798 v4 pith:APVX25DV submitted 2017-04-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords bayesiannetworksneuralrecurrentrnnsbenchmarkdemonstratelanguage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this work we explore a straightforward variational Bayes scheme for Recurrent Neural Networks. Firstly, we show that a simple adaptation of truncated backpropagation through time can yield good quality uncertainty estimates and superior regularisation at only a small extra computational cost during training, also reducing the amount of parameters by 80\%. Secondly, we demonstrate how a novel kind of posterior approximation yields further improvements to the performance of Bayesian RNNs. We incorporate local gradient information into the approximate posterior to sharpen it around the current batch statistics. We show how this technique is not exclusive to recurrent neural networks and can be applied more widely to train Bayesian neural networks. We also empirically demonstrate how Bayesian RNNs are superior to traditional RNNs on a language modelling benchmark and an image captioning task, as well as showing how each of these methods improve our model over a variety of other schemes for training them. We also introduce a new benchmark for studying uncertainty for language models so future methods can be easily compared.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures

    stat.ML 2019-08 conditional novelty 6.0 of 10

    A mixture of Bezier curves with Gaussian control points, trained with a mixture density network, generates smooth multi-modal sequences in one inference step and outperforms comparable baselines on two tasks.

  2. Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement

    cs.CV 2025-05 reject novelty 5.0 of 10

    GRAD fuses spatial, wavelet, and Fourier visual features with kinematic robot data through graph attention and adversarial alignment, and reports top accuracy plus improved corruption tolerance on two surgical gesture...

  3. Error-quantified Conformal Inference for Time Series

    stat.ML 2025-02 conditional novelty 5.0 of 10

    ECI adds a smoothed error-quantification term to the online conformal update rule and proves distribution-free long-run coverage bounds, yielding tighter prediction sets on real time-series benchmarks.

  4. U-CAM: Visual Explanation using Uncertainty based Class Activation Maps

    cs.CV 2019-08 conditional novelty 5.0 of 10

    U-CAM uses gradients of aleatoric and predictive uncertainty losses to sharpen visual attention maps and improve VQA accuracy over standard baselines.

  5. Bayesian Learning in Structural Dynamics: A Comprehensive Review and Emerging Trends

    physics.data-an 2025-05 conditional novelty 4.0 of 10

    A comprehensive review that organizes Bayesian inference in structural dynamics into physical model learning and data-centric statistical model learning, with applications and open challenges.

  6. Alternators With Noise Models

    cs.LG 2025-05 reject novelty 4.0 of 10

    Alternator++ adds trainable noise-prediction networks and a noise-matching loss to Alternators, but the proposed training target is ill-defined and the reported improvements are mixed.

  7. A Statistical Framework for Model Selection in LSTM Networks

    stat.ML 2025-06 reject novelty 2.0 of 10

    A statistical model selection framework for LSTMs is proposed, but it largely recombines existing methods and provides no convincing evidence of improvement.

Pith tools