检索结果-内蒙古大学图书馆

25th Australasian Software Engineering Conference (ASWEC)

作者： Alhefdhi, Abdulaziz Dam, Hoa Khanh Hata, Hideaki Ghose, Aditya Univ Wollongong Wollongong NSW Australia Nara Inst Sci & Technol Ikoma Japan

ISBN: (纸本)9781728112411

Pseudo-code written in natural language and mathematical expressions is a useful description of source code. Pseudocode aids programmers in understanding the code written in a programming language they are not familiar with. However, writing pseudo-code for each code statement is labour intensive. In this paper, we propose a novel approach to automatically generate pseudo-code from source code using Neural Machine Translation. Our model is built upon the deep learning encoder-decoder using the attention-based Long Short-Term Memory architecture to capture the long-term dependencies in both source code and pseudo-code. An empirical evaluation on a real Python dataset demonstrates the applicability of our approach in practice.

关键词： pseudo-code encoder-decoder seq2seq documentation lstm

来源：评论

学校读者我要写书评

暂无评论

创新构想话题生成

引用

山西大学学报(自然科学版) 2019年第1期42卷 51-58页

作者：陈丽娟兰艳艳庞亮李家宁郭嘉丰徐君程学旗中国科学院计算技术研究所中国科学院网络数据科学与技术重点实验室

文章提出了创新构想话题的自动生成任务,主动生成具有新颖性、权威性的话题,能够激发群体讨论热情,有助于推动相关领域的发展。以encoder-decoder文本生成技术为基础,构建了一套创新构想话题生成框架。首先通过实时爬取相关网站的内容,... 详细信息

文章提出了创新构想话题的自动生成任务,主动生成具有新颖性、权威性的话题,能够激发群体讨论热情,有助于推动相关领域的发展。以encoder-decoder文本生成技术为基础,构建了一套创新构想话题生成框架。首先通过实时爬取相关网站的内容,作为信息获取的主要来源;然后利用数据分析工具提取文本的关键词和摘要,使用了TF-IDF算法和TextRank算法;最后利用训练好的话题生成模型得到话题表达。实验结果展示了生成的创新构想话题,说明基于该文提出的流程可以有效挖掘文档中潜在的话题。

关键词：创新构想话题 encoder-decoder 话题生成模型 TextRank

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Segmentation of Multiple Retinal Pathologies Using Fully Convolutional Deep Neural Network 22nd

Simultaneous Segmentation of Multiple Retinal Pathologies Us...

引用

22nd Conference on Medical Image Understanding and Analysis (MIUA)

作者： Badar, Maryam Shahzad, M. Fraz, M. M. Natl Univ Sci & Technol Sch Elect Engn & Comp Sci Islamabad Pakistan

ISBN: (纸本)9783319959214;9783319959207

The segmentation of retinal pathologies is the primitive and essential step in the development of automated diagnostic system for various systemic, cardiovascular, and ophthalmic diseases. The existing state-of-the-art machine learning based retinal pathologic segmentation techniques mainly aim at delineating pathology of one kind only. In this context, we have proposed a novel end-to-end technique for simultaneous segmentation of multiple retinal pathologies (i.e., exudates, hemorrhages, and cotton-wool spots) using encoder-decoder based fully convolutional neural network architecture. Moreover, the task of retinal pathology extraction has been modeled as a semantic segmentation framework which enables us to obtain pixel-level class labels. The proposed algorithm has been evaluated on publically available Messidor dataset and achieved state-of-the-art mean accuracies of 99.24% (exudates), 97.86% (hemorrhages), and 88.65% (cotton-wool spots). The developed approach may aid in further optimization of pathology quantification module of the QUARTZ software which has been developed earlier by our research group.

关键词： Retinal pathology Diabetic retinopathy Deep learning Fully convolutional neural networks encoder-decoder Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Using Multi-task and Transfer Learning to Solve Working Memory Tasks 17

Using Multi-task and Transfer Learning to Solve Working Memo...

引用

17th IEEE International Conference on Machine Learning and Applications (IEEE ICMLA)

作者： Jayram, T. S. Kornuta, Tomasz McAvoy, Ryan L. Ozcan, Ahmet S. IBM Res Almaden San Jose CA 95120 USA

ISBN: (纸本)9781538668054

We propose a new architecture called Memory-Augmented encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside the encoder and solver, respectively, that interface with a shared memory module and is completely differentiable. We study different types of encoders in a systematic manner and demonstrate a unique advantage of multi-task learning in obtaining the best possible encoder. We show by extensive experimentation that the trained MAES models achieve task-size generalization, i.e., they are capable of handling sequential inputs 50 times longer than seen during training, with appropriately large memory modules. We demonstrate that the performance achieved by MAES far outperforms existing and well-known models such as the LSTM, NTM and DNC on the entire suite of tasks.

关键词： encoder-decoder memory-augmented neural networks working memory transfer learning

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation with Recurrent Highway Networks 6th

Neural Machine Translation with Recurrent Highway Networks

引用

6th International Conference on Mining Intelligence and Knowledge Exploration (MIKE)

作者： Parmar, Maulik Devi, V. Susheela Indian Inst Sci Bengaluru 560012 Karnataka India

ISBN: (纸本)9783030059187;9783030059170

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 encoder is used to project the source sentence to a fixed dimensional vector and then another deep LSTM decodes the target sentence from the vector. However there has been very little work on exploring architectures that have more than one layer in space (i.e. in each time step). This paper examines the effectiveness of the simple Recurrent Highway Networks (RHN) in NMT tasks. The model uses Recurrent Highway Neural Network in encoder and decoder, with attention. We also explore the reconstructor model to improve adequacy. We demonstrate the effectiveness of all three approaches on the IWSLT English-Vietnamese dataset. We see that RHN performs on par with LSTM based models and even better in some cases. We see that deep RHN models are easy to train compared to deep LSTM based models because of highway connections. The paper also investigates the effects of increasing recurrent depth in each time step.

关键词： Recurrent highway networks Reconstructor Attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

ACOUSTIC-TO-WORD RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODELS

ACOUSTIC-TO-WORD RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODEL...

引用

IEEE Workshop on Spoken Language Technology (SLT)

作者： Palaskar, Shruti Metze, Florian Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA

ISBN: (纸本)9781538643341

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0% in Word Error Rate on the Switchboard corpus compared to prior work. In addition to these promising results, word-based models are more interpretable than character models, which have to be composed into words using a separate decoding step. We analyze the encoder hidden states and the attention behavior, and show that location-aware attention naturally represents words as a single speech-word-vector, despite spanning multiple frames in the input. We finally show that the Acoustic-to-Word model also learns to segment speech into words with a mean standard deviation of 3 frames as compared with human annotated forced-alignments for the Switchboard corpus.

关键词： end-to-end speech recognition encoder-decoder acoustic-to-word speech embeddings

来源：评论

学校读者我要写书评

暂无评论

CrossNet: An End-to-End Reference-Based Super Resolution Network Using Cross-Scale Warping 15th

CrossNet: An End-to-End Reference-Based Super Resolution Net...

引用

15th European Conference on Computer Vision (ECCV)

作者： Zheng, Haitian Ji, Mengqi Wang, Haoqian Liu, Yebin Fang, Lu Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Beijing Peoples R China Hong Kong Univ Sci & Technol Clear Water Bay Hong Kong Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China

ISBN: (纸本)9783030012311;9783030012304

The Reference-based Super-resolution (RefSR) super-resolves a low-resolution (LR) image given an external high-resolution (HR) reference image, where the reference image and LR image share similar viewpoint but with significant resolution gap (8x). Existing RefSR methods work in a cascaded way such as patch matching followed by synthesis pipeline with two independently defined objective functions, leading to the inter-patch misalignment, grid effect and inefficient optimization. To resolve these issues, we present CrossNet, an end-to-end and fully-convolutional deep neural network using cross-scale warping. Our network contains image encoders, cross-scale warping layers, and fusion decoder: the encoder serves to extract multi-scale features from both the LR and the reference images;the cross-scale warping layers spatially aligns the reference feature map with the LR feature map;the decoder finally aggregates feature maps from both domains to synthesize the HR output. Using cross-scale warping, our network is able to perform spatial alignment at pixel-level in an end-to-end fashion, which improves the existing schemes [1,2] both in precision (around 2 dB-4 dB) and efficiency (more than 100 times faster).

关键词： Reference-based Super Resolution Light field imaging Image synthesis encoder-decoder Optical flow

来源：评论

学校读者我要写书评

暂无评论

Aerial Image Semantic Segmentation Using Spatial and Channel Attention

Aerial Image Semantic Segmentation Using Spatial and Channel...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Zhu Lan Qingqing Huang Fen Chen Yu Meng School of Resources and Environment University of Electronic Science and Technology of China Chengdu China Aerospace Information Research Institute Chinese Academy of Science Beijing China

ISBN: (纸本)9781728123264

With the development of sensor, remote sensing has become an effective way to observe the Earth. Land cover classification is an important application of remote sensing data. Deep convolutional neural networks (DCNN) have good capability to extract effective image feature. In this paper, an automatic land cover classification method using spatial and channel attention was proposed. encoder-decoder structure was adopted as the network architecture. We used "channel attention" to enhance the function of effective channels. By using "spatial attention" to combining high-level semantic features with low-level features, better land objects boundaries were obtained. The proposed method was tested on ISPRS Potsdam 2D-Semantic Segmentation Challenge Dataset. The results showed that our proposed method, which uses spatial and channel attention with atrous spatial pyramid attention networks (SA-ASPA) outperforms the Deeplab_v3+ in terms of mean Intersection over Union (mIoU) for 5%.

关键词： Semantic segmentation Deep convolution neural networks encoder-decoder Channel attention Spatial attention NETWORK STRUCTURE image feature aerial images Semantics LOW LEVEL Space Autoland

来源：评论

学校读者我要写书评

暂无评论

FORWARD ATTENTION IN SEQUENCE-TO-SEQUENCE ACOUSTIC MODELING FOR SPEECH SYNTHESIS

FORWARD ATTENTION IN SEQUENCE-TO-SEQUENCE ACOUSTIC MODELING ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Jing-Xuan Ling, Zhen-Hua Dai, Li-Rong Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China

ISBN: (纸本)9781538646588

This paper proposes a forward attention method for the sequence-to-sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment paths that satisfy the monotonic condition are taken into consideration at each decoder timestep. The modified attention probabilities at each timestep are computed recursively using a forward algorithm. A transition agent for forward attention is further proposed, which helps the attention mechanism to make decisions whether to move forward or stay at each decoder timestep. Experimental results show that the proposed forward attention method achieves faster convergence speed and higher stability than the baseline attention method. Besides, the method of forward attention with transition agent can also help improve the naturalness of synthetic speech and control the speed of synthetic speech effectively.

关键词： sequence-to-sequence model encoder-decoder attention speech synthesis

来源：评论

学校读者我要写书评

暂无评论

GLADNet: Low-Light Enhancement Network with Global Awareness 13

GLADNet: Low-Light Enhancement Network with Global Awareness

引用

13th IEEE International Conference on Automatic Face & Gesture Recognition (FG)

作者： Wang, Wenjing Wei, Chen Yang, Wenhan Liu, Jiaying Peking Univ Inst Comp Sci & Technol Beijing Peoples R China

ISBN: (纸本)9781538623350

In this paper, we address the problem of low light enhancement. Our key idea is to first calculate a global illumination estimation for the low-light input, then adjust the illumination under the guidance of the estimation and supplement the details using a concatenation with the original input. Considering that, we propose a GLobal illumination Aware and Detail-preserving Network (GLADNet). The input image is rescaled to a certain size and then put into an encoder-decoder network to generate global priori knowledge of the illumination. Based on the global prior and the original input image, a convolutional network is employed for detail reconstruction. For training GLADNet, we use a synthetic dataset generated from RAW images. Extensive experiments demonstrate the superiority of our method over other compared methods on the real low-light images captured in various conditions.

关键词： Low-light enhancement deep learning detail reconstruction encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：