paper-with-me

홈 › Papers

Regularizing RNNs by Stabilizing Activations

2015-11-26 · David Krueger, Roland Memisevic

We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperforming weight noise and dropout. We achieve competitive performance (18.6\% PER) on the TIMIT phoneme recognition task for RNNs evaluated without beam search or an RNN transducer. With this penalty term, IRNN can achieve similar performance to LSTM on language modeling, although adding the penalty term to the LSTM results in superior performance. Our penalty term also prevents the exponential growth of IRNN's activations outside of their training horizon, allowing them to generalize to much longer sequences.

📄 PDF Abstract BibTeX arXiv:1511.08400

Code (1)

vimarshc/fastai_experiments tf

Tasks

Language ModelingLanguage ModellingPhoneme Recognition

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

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

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations

2016-05-23 · NeurIPS 2016 12 · Behnam Neyshabur, Yuhuai Wu, Ruslan Salakhutdinov, Nathan Srebro

We investigate the parameter-space geometry of recurrent neural networks (RNNs), and develop an adaptation of path-SGD optimization method, attuned to this geometry, that can learn plain RNNs with ReLU activations. On se…

Input-Output Equivalence of Unitary and Contractive RNNs

2019-10-30 · M. Emami, M. Sahraee-Ardakan, S. Rangan, A. K. Fletcher

Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the u…

Input-Output Equivalence of Unitary and Contractive RNNs

2019-12-01 · NeurIPS 2019 12 · Melikasadat Emami, Mojtaba Sahraee Ardakan, Sundeep Rangan, Alyson K. Fletcher

Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the u…

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

2023-12-28 · NeurIPS 2023 11 · Rainer Engelken

Training recurrent neural networks (RNNs) remains a challenge due to the instability of gradients across long time horizons, which can lead to exploding and vanishing gradients. Recent research has linked these problems …