paper-with-me

홈 › Papers

Semi-tied Units for Efficient Gating in LSTM and Highway Networks

2018-06-18 · Chao Zhang, Philip Woodland

Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network. Although gating is powerful, it is rather expensive in terms of both computation and storage as each gating unit uses a separate full weight matrix. This issue can be severe since several gates can be used together in e.g. an LSTM cell. This paper proposes a semi-tied unit (STU) approach to solve this efficiency issue, which uses one shared weight matrix to replace those in all the units in the same layer. The approach is termed "semi-tied" since extra parameters are used to separately scale each of the shared output values. These extra scaling factors are associated with the network activation functions and result in the use of parameterised sigmoid, hyperbolic tangent, and rectified linear unit functions. Speech recognition experiments using British English multi-genre broadcast data showed that using STUs can reduce the calculation and storage cost by a factor of three for highway networks and four for LSTMs, while giving similar word error rates to the original models.

📄 PDF Abstract BibTeX arXiv:1806.06513

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Highway networks There is plenty of theoretical and empirical evidence that depth of neural networks is a crucial ingredient for their success. However, network training becomes more difficult…
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

Highway Transformer: Self-Gating Enhanced Self-Attentive Networks

2020-04-17 · ACL 2020 6 · Yekun Chai, Shuo Jin, Xinwen Hou

Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different lo…

Faster Training of Very Deep Networks Via p-Norm Gates

2016-08-11 · Trang Pham, Truyen Tran, Dinh Phung, Svetha Venkatesh

A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gat…

Machine TranslationTranslation

X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction

2025-10-31 · Aanchal Rajesh Chugh, Marion Neumeier, Sebastian Dorn arxiv

Accurate trajectory prediction is crucial for safe and reliable autonomous driving systems, requiring models that capture long-term temporal dependencies while accounting for social interactions among neighboring vehicle…

Trajectory PredictionAutonomous Driving

Graph Highway Networks

2020-04-09 · Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose

Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. However, they suffer from the notorious over-smoothing problem, in which the learned represent…

Training Very Deep Networks

2015-07-22 · NeurIPS 2015 12 · Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and training of very deep networks remains an open…

Image Classification