paper-with-me

Papers

Going Wider: Recurrent Neural Network With Parallel Cells

2017-05-03 · Danhao Zhu, Si Shen, Xin-yu Dai, Jia-Jun Chen

Recurrent Neural Network (RNN) has been widely applied for sequence modeling. In RNN, the hidden states at current step are full connected to those at previous step, thus the influence from less related features at previous step may potentially decrease model's learning ability. We propose a simple technique called parallel cells (PCs) to enhance the learning ability of Recurrent Neural Network (RNN). In each layer, we run multiple small RNN cells rather than one single large cell. In this paper, we evaluate PCs on 2 tasks. On language modeling task on PTB (Penn Tree Bank), our model outperforms state of art models by decreasing perplexity from 78.6 to 75.3. On Chinese-English translation task, our model increases BLEU score for 0.39 points than baseline model.

📄 PDF Abstract BibTeX arXiv:1705.01346

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingTranslation

Similar Papers 제목 키워드 기반

Dilated Recurrent Neural Networks

2017-10-05 · NeurIPS 2017 12 · Shiyu Chang, Yang Zhang, Wei Han, Mo Yu 외

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallel…

Sequential Image Classification

Go Wider Instead of Deeper

2021-07-25 · Fuzhao Xue, Ziji Shi, Futao Wei, Yuxuan Lou 외

More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by …

Image ClassificationMixture-of-Experts

Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring

2020-10-02 · An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn 외

Predictive business process monitoring (PBPM) aims to predict future process behavior during ongoing process executions based on event log data. Especially, techniques for the next activity and timestamp prediction can h…

Parallel Long Short-Term Memory for Multi-stream Classification

2017-02-11 · Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, Georges Linarès 외

Recently, machine learning methods have provided a broad spectrum of original and efficient algorithms based on Deep Neural Networks (DNN) to automatically predict an outcome with respect to a sequence of inputs. Recurre…

ClassificationGeneral Classification

Thick-Net: Parallel Network Structure for Sequential Modeling

2019-11-19 · Yu-Xuan Li, Jin-Yuan Liu, Liang Li, Xiang Guan

Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper structures. However, the former becomes mor…

Language ModelingLanguage Modellingtext-classificationText Classification