paper-with-me

Papers

Batch-normalized Recurrent Highway Networks

2018-09-26 · Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the problem of vanishing or exploding gradients. They achieve this by setting the eigenvalues of the temporal Jacobian to 1 across the time steps. In this work, batch normalized recurrent highway networks are proposed to control the gradient flow in an improved way for network convergence. Specifically, the introduced model can be formed by batch normalizing the inputs at each recurrence loop. The proposed model is tested on an image captioning task using MSCOCO dataset. Experimental results indicate that the batch normalized recurrent highway networks converge faster and performs better compared with the traditional LSTM and RHN based models.

📄 PDF Abstract BibTeX arXiv:1809.10271

Code (1)

KurochkinAlexey/Hierarchical-Attention-Based-Recurrent-Highway-Networks-for-Time-Series-Prediction pytorch

Tasks

Image Captioning

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

Recurrent Batch Normalization

2016-03-30 · Tim Cooijmans, Nicolas Ballas, César Laurent, Çağlar Gülçehre 외

We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the input-to-hidden transformation of RNNs, w…

General ClassificationLanguage ModelingLanguage ModellingQuestion Answering+2

Batch Normalized Recurrent Neural Networks

2015-10-05 · César Laurent, Gabriel Pereyra, Philémon Brakel, Ying Zhang 외

Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent …

Language Modellingspeech-recognitionSpeech Recognition

Learning text representation using recurrent convolutional neural network with highway layers

2016-06-22 · Ying Wen, Wei-Nan Zhang, Rui Luo, Jun Wang

Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Net…

Sentiment Analysis

Neural Machine Translation with Recurrent Highway Networks

2019-04-28 · Maulik Parmar, V. Susheela Devi

Recurrent Neural Networks have lately gained a lot of popularity in language modelling tasks, especially in neural machine translation(NMT). Very recent NMT models are based on Encoder-Decoder, where a deep LSTM based en…

DecoderLanguage ModellingMachine TranslationNMT+2

Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer

2019-03-21 · Ting-Rui Chiang, Chao-Wei Huang, Shang-Yu Su, Yun-Nung Chen

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine th…

Response GenerationSentence