paper-with-me

Papers

Parallelizable Stack Long Short-Term Memory

2019-04-06 · WS 2019 6 · Shuoyang Ding, Philipp Koehn

Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously difficult to parallelize for GPU training due to the fact that the computations are dependent on discrete operations. In this paper, we tackle this problem by utilizing state access patterns of StackLSTM to homogenize computations with regard to different discrete operations. Our parsing experiments show that the method scales up almost linearly with increasing batch size, and our parallelized PyTorch implementation trains significantly faster compared to the Dynet C++ implementation.

📄 PDF Abstract BibTeX arXiv:1904.03409

Code (1)

shuoyangd/hoolock 공식 구현 pytorch

Tasks

GPUMachine TranslationTranslation

Similar Papers 제목 키워드 기반

xLSTM: Extended Long Short-Term Memory

2024-05-07 · Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer 외

In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning succ…

Language ModelingLanguage ModellingState Space Models

Vision-LSTM: xLSTM as Generic Vision Backbone

2024-06-06 · Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter 외

Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performa…

Titans: Learning to Memorize at Test Time

2024-12-31 · Ali Behrouz, Peilin Zhong, Vahab Mirrokni

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden st…

Common Sense ReasoningLanguage ModelingLanguage Modelling

Time Series Forecasting with Stacked Long Short-Term Memory Networks

2020-11-02 · Frank Xiao

Long Short-Term Memory (LSTM) networks are often used to capture temporal dependency patterns. By stacking multi-layer LSTM networks, it can capture even more complex patterns. This paper explores the effectiveness of ap…

Time SeriesTime Series AnalysisTime Series ForecastingTime Series Prediction

Long Short Term Memory Networks for Anomaly Detection in Time Series

2015-04-22 · ESANN 2015 4 · Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, Puneet Agarwal

Long Short Term Memory (LSTM) networks have been demonstrated to be particularly useful for learning sequences containing longer term patterns of unknown length, due to their ability to maintain long term memory. Stackin…

Anomaly DetectionFault DetectionTime SeriesTime Series Anomaly Detection