paper-with-me

홈 › Papers

Learning Longer-term Dependencies in RNNs with Auxiliary Losses

2018-07-01 · ICML 2018 7 · Trieu Trinh, Andrew Dai, Thang Luong, Quoc Le

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability to capture long term dependencies in RNNs by adding an unsupervised auxiliary loss to the original objective. This auxiliary loss forces RNNs to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full BPTT. We evaluate our method on a variety of settings, including pixel-by-pixel image classification with sequence lengths up to 16000, and a real document classification benchmark. Our results highlight good performance and resource efficiency of this approach over competitive baselines, including other recurrent models and a comparable sized Transformer. Further analyses reveal beneficial effects of the auxiliary loss on optimization and regularization, as well as extreme cases where there is little to no backpropagation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Document ClassificationGeneral Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Learning Longer-term Dependencies in RNNs with Auxiliary Losses

2018-03-01 · ICML 2018 · Trieu H. Trinh, Andrew M. Dai, Minh-Thang Luong, Quoc V. Le

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is diffi…

Document ClassificationGeneral Classificationimage-classificationImage Classification

Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses

2019-10-11 · Asier Mujika, Felix Weissenberger, Angelika Steger

Learning long-term dependencies is a key long-standing challenge of recurrent neural networks (RNNs). Hierarchical recurrent neural networks (HRNNs) have been considered a promising approach as long-term dependencies are…

Achieving Online Regression Performance of LSTMs with Simple RNNs

2020-05-16 · N. Mert Vural, Fatih Ilhan, Selim F. Yilmaz, Salih Ergüt 외

Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred i…

regression

Convolutions Are All You Need (For Classifying Character Sequences)

2018-11-01 · WS 2018 11 · Zach Wood-Doughty, Nicholas Andrews, Mark Dredze

While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, …

AllClassificationDocument ClassificationGeneral Classification+5

Learning Longer-term Dependencies via Grouped Distributor Unit

2019-04-29 · Wei Luo, Feng Yu

Learning long-term dependencies still remains difficult for recurrent neural networks (RNNs) despite their success in sequence modeling recently. In this paper, we propose a novel gated RNN structure, which contains only…