paper-with-me

홈 › Papers

Noise-Based Regularizers for Recurrent Neural Networks

2018-01-01 · ICLR 2018 1 · Adji B. Dieng, Jaan Altosaar, Rajesh Ranganath, David M. Blei

Recurrent neural networks (RNNs) are powerful models for sequential data. They can approximate arbitrary computations, and have been used successfully in domains such as text and speech. However, the flexibility of RNNs makes them susceptible to overfitting and regularization is important. We develop a noise-based regularization method for RNNs. The idea is simple and easy to implement: we inject noise in the hidden units of the RNN and then maximize the original RNN's likelihood averaged over the injected noise. On a language modeling benchmark, our method achieves better performance than the deterministic RNN and the variational dropout.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Tikhonov Regularization for Long Short-Term Memory Networks

2017-08-09 · Andrei Turkin

It is a well-known fact that adding noise to the input data often improves network performance. While the dropout technique may be a cause of memory loss, when it is applied to recurrent connections, Tikhonov regularizat…

Regularizing Recurrent Networks - On Injected Noise and Norm-based Methods

2014-10-21 · Saahil Ognawala, Justin Bayer

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to fee…

Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms

2023-08-21 · Alexis Goujon, Sebastian Neumayer, Michael Unser

We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus. Such regularizers give rise to variational denoisers that minimize a convex energy. They rely on few parameters (…

Image ReconstructionMRI Reconstruction

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

2016-06-03 · David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki 외

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ens…

Language Modelling

QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem

2026-06-18 · Merijn Moody, Zier Mensch, Miranda C. N. Cheng, Peter G. Bolhuis 외 arxiv

Reliable quantum control in the presence of decoherence requires policies that combat the effect of environmental noise on the controlled dynamics. Open quantum systems under continuous monitoring generate classical meas…