paper-with-me

Papers

Parallelizing Linear Recurrent Neural Nets Over Sequence Length

2017-09-12 · ICLR 2018 1 · Eric Martin, Chris Cundy

Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length. We show the training of RNNs with only linear sequential dependencies can be parallelized over the sequence length using the parallel scan algorithm, leading to rapid training on long sequences even with small minibatch size. We develop a parallel linear recurrence CUDA kernel and show that it can be applied to immediately speed up training and inference of several state of the art RNN architectures by up to 9x. We abstract recent work on linear RNNs into a new framework of linear surrogate RNNs and develop a linear surrogate model for the long short-term memory unit, the GILR-LSTM, that utilizes parallel linear recurrence. We extend sequence learning to new extremely long sequence regimes that were previously out of reach by successfully training a GILR-LSTM on a synthetic sequence classification task with a one million timestep dependency.

📄 PDF Abstract BibTeX arXiv:1709.04057

Code (2)

eamartin/parallelizing_linear_rnns 공식 구현 tf
proger/accelerated-scan pytorch

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Parallelizing non-linear sequential models over the sequence length

2023-09-21 · Yi Heng Lim, Qi Zhu, Joshua Selfridge, Muhammad Firmansyah Kasim

Sequential models, such as Recurrent Neural Networks and Neural Ordinary Differential Equations, have long suffered from slow training due to their inherent sequential nature. For many years this bottleneck has persisted…

GPUTime SeriesTime Series Classification

A Context-aware Convolutional Natural Language Generation model for Dialogue Systems

2018-07-01 · WS 2018 7 · Sourab Mangrulkar, Suhani Shrivastava, Veena Thenkanidiyoor, Dileep Aroor Dinesh

Natural language generation (NLG) is an important component in spoken dialog systems (SDSs). A model for NLG involves sequence to sequence learning. State-of-the-art NLG models are built using recurrent neural network (R…

Machine TranslationSemantic correspondenceSpoken Dialogue SystemsText Generation+1

Parallelizing Legendre Memory Unit Training

2021-02-22 · Narsimha Chilkuri, Chris Eliasmith

Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant…

Machine TranslationSentiment AnalysisSequential Image ClassificationTranslation

DeepPCR: Parallelizing Sequential Operations in Neural Networks

2023-09-28 · NeurIPS 2023 11

Parallelization techniques have become ubiquitous for accelerating inference and training of deep neural networks. Despite this, several operations are still performed in a sequential manner. For instance, the forward an…

Denoising

How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems

2019-10-05 · EMNLP (IWSLT) 2019 11 · Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen, Le-Minh Nguyen

While translating between East Asian languages, many works have discovered clear advantages of using characters as the translation unit. Unfortunately, traditional recurrent neural machine translation systems hinder the …

Machine TranslationTranslation