paper-with-me

Papers

Improving Language Modeling using Densely Connected Recurrent Neural Networks

2017-07-19 · WS 2017 8 · Fréderic Godin, Joni Dambre, Wesley De Neve

In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2-layer LSTM model trained with dropout (Zaremba et al. 2014). In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.

📄 PDF Abstract BibTeX arXiv:1707.06130

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information

2018-05-29 · Seonhoon Kim, Inho Kang, Nojun Kwak

Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship b…

Natural Language InferenceParaphrase IdentificationQuestion AnsweringSentence

Densely Connected Attention Propagation for Reading Comprehension

2018-11-10 · NeurIPS 2018 12 · Yi Tay, Luu Anh Tuan, Siu Cheung Hui, Jian Su

We propose DecaProp (Densely Connected Attention Propagation), a new densely connected neural architecture for reading comprehension (RC). There are two distinct characteristics of our model. Firstly, our model densely c…

AllOpen-Domain Question AnsweringQuestion AnsweringReading Comprehension

Character-Level Feature Extraction with Densely Connected Networks

2018-06-24 · COLING 2018 8 · Chanhee Lee, Young-Bum Kim, Dongyub Lee, Heuiseok Lim

Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generating hand-crafted features, methods that ut…

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+3

Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning

2025-10-02 · Jinshu Huang, Haibin Su, Xue-Cheng Tai, Chunlin Wu arxiv

In deep learning, dense layer connectivity has become a key design principle in deep neural networks (DNNs), enabling efficient information flow and strong performance across a range of applications. In this work, we mod…

A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation

2022-09-15 · Zhanpeng Shao, Wen Zhou, Wuzhen Wang, Jianyu Yang 외

Event camera is an emerging bio-inspired vision sensors that report per-pixel brightness changes asynchronously. It holds noticeable advantage of high dynamic range, high speed response, and low power budget that enable …

Pose Estimation