检索结果-内蒙古大学图书馆

Clustered Multi-Task sequence-to-sequence Learning for Autonomous Vehicle Repositioning

IEEE ACCESS 2021年 9卷 14504-14515页

作者： Lee, Sangmin Lim, Dae-Eun Kang, Younkook Kim, Hae Joong Kwangwoon Univ Sch Informat Convergence Seoul 01897 South Korea Kangwon Natl Univ Dept Ind Engn Chunchon 24341 South Korea Samsung Elect Mat Handling Automat Grp Hwaseong 445330 South Korea

Clustered multi-task learning, which aims to leverage the generalization performance over clustered tasks, has shown an outstanding performance in various machine learning applications. In this paper, a clustered multi-task sequence-to-sequence learning (CMSL) for autonomous vehicle systems (AVSs) in large-scale semiconductor fabrications (fab) is proposed, where AVSs are widely used for wafer transfers. Recently, as fabs become larger, the repositioning of idle vehicles to where they may be requested has become a significant challenge because inefficient vehicle balancing leads to transfer delays, resulting in production machine idleness. However, existing vehicle repositioning systems are mainly controlled by human operators, and it is difficult for such systems to guarantee efficiency. Further, we should handle the small data problem, which is insufficient for machine learning because of the irregular time-varying manufacturing environments. The main purpose of this study is to examine CMSL-based predictive control of idle vehicle repositioning to maximize machine utilization. We conducted an experimental evaluation to compare the prediction accuracy of CMSL with existing methods. Further, a case study in a real largescale semiconductor plant, demonstrated that the proposed predictive approach outperforms the existing approaches in terms of transfer efficiency and machine utilization.

关键词： Task analysis Vehicle dynamics Delays Prediction algorithms Layout Resource management Heuristic algorithms Clustered multi-task learning sequence-to-sequence vehicle repositioning idle vehicle balancing automated material handling systems overhead hoist transports

来源：评论

学校读者我要写书评

暂无评论

Robust Text Image Recognition via Adversarial sequence-to-sequence Domain Adaptation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 3922-3933页

作者： Zhang, Yaping Nie, Shuai Liang, Shan Liu, Wenju Chinese Acad Sci CASIA Natl Lab Pattern Recognit Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci UCAS Sch Artificial Intelligence Beijing Peoples R China

Robust text reading is a very challenging problem, due to the distribution of text images changing significantly in real-world scenarios. One effective solution is to align the distribution between different domains by domain adaptation methods. However, we found that these methods might struggle when dealing sequence-like text images. An important reason is that conventional domain adaptation methods strive to align images as a whole, while text images consist of variable-length fine-grained character information. To address this issue, we propose a novel Adversarial sequence-to-sequence Domain Adaptation (ASSDA) method to learn "where to adapt" and "how to align" the sequential image. Our key idea is to mine the local regions that contain characters, and focus on aligning them across domains in an adversarial manner. Extensive text recognition experiments show the ASSDA could efficiently transfer sequence knowledge and validate the promising power towards the various domain shift in the real world applications.

关键词： Text recognition Image recognition Adaptation models Task analysis Character recognition Training Visualization sequence-to-sequence domain adaptation text image recognition

来源：评论

学校读者我要写书评

暂无评论

SPT-Code: sequence-to-sequence Pre-Training for Learning Source Code Representations 22

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Sou...

引用

ACM/IEEE 44th International Conference on Software Engineering (ICSE)

作者： Niu, Changan Li, Chuanyi Ng, Vincent Ge, Jidong Huang, Liguo Luo, Bin Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Univ Texas Dallas Human Language Technol Res Inst Richardson TX 75083 USA Southern Methodist Univ Dept Comp Sci Dallas TX USA

ISBN: (纸本)9781450392211

Recent years have seen the successful application of large pretrained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-art models such as T5-learning, simply reuse the pretraining tasks designed for natural languages. Moreover, to learn the natural language description of source code needed eventually for code-related tasks such as code summarization, existing pretraining tasks require a bilingual corpus composed of source code and the associated natural language description, which severely limits the amount of data for pre-training. To this end, we propose SPT-Code, a sequence-to-sequence pre-trained model for source code. In order to pre-train SPT-Code in a sequence-to-sequence manner and address the aforementioned weaknesses associated with existing pre-training tasks, we introduce three pre-training tasks that are specifically designed to enable SPT-Code to learn knowledge of source code, the corresponding code structure, as well as a natural language description of the code without relying on any bilingual corpus, and eventually exploit these three sources of information when it is applied to downstream tasks. Experimental results demonstrate that SPT-Code achieves state-of-the-art performance on five code-related downstream tasks after fine-tuning.

关键词： pre-training code representation learning sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence models for workload interference prediction on batch processing datacenters

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2020年 110卷 155-166页

作者： Buchaca, David Marcual, Joan LLuis Berral, Josep Carrera, David BSC C Jordi Girona 1-3 Barcelona 08034 Spain UPC BarcelonaTECH Barcelona Spain

Co-scheduling of jobs in data centers is a challenging scenario where jobs can compete for resources, leading to severe slowdowns or failed executions. Efficient job placement on environments where resources are shared requires awareness on how jobs interfere during execution, to go far beyond ineffective resource overbooking techniques. Current techniques, most of which already involve machine learning and job modeling, are based on workload behavior summarization over time, rather than focusing on effective job requirements at each instant of the execution. In this work, we propose a methodology for modeling co-scheduling of jobs on data centers, based on their behavior towards resources and execution time and using sequence-to-sequence models based on recurrent neural networks. The goal is to forecast co-executed jobs footprint on resources throughout their execution time, from the profile shown by the individual jobs, in order to enhance resource manager and scheduler placement decisions. The methods presented herein are validated by using High Performance Computing benchmarks based on different frameworks (such as Hadoop and Spark) and applications (CPU bound, IO bound, machine learning, SQL queries...). Experiments show that the model can correctly identify the resource usage trends from previously seen and even unseen co-scheduled jobs. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Resource management sequence-to-sequence Workload interference Deep learning Workload placement

来源：评论

学校读者我要写书评

暂无评论

A sequence-to-sequence model for joint bridge response forecasting

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2023年第1期203卷

作者： Bahrami, Omid Wang, Wentao Hou, Rui Lynch, Jerome P. Univ Michigan Depart Civil & Env Engn Ann Arbor MI 48109 USA Duke Univ Depart Civil & Env Engn Durham NC 27780 USA Univ Michigan Dept Civil & Environm Engn 2160 G G Brown Bldg Ann Arbor MI 48109 USA

Knowledge of the structural response of bridges is extremely important for highway asset management and bridge structural health monitoring. Instrumenting every bridge in a road network and maintaining the monitoring instrumentation over decades of service can be financially infeasible. Mechanical intuition suggests a significant relationship exists between responses of two sets of bridges reasonably similar in design exposed to an identical load. This study explores the use of data-driven models to forecast the response of one bridge to a given truck load using the response of another bridge to the same loading profile. By deploying a modern monitoring system in multiple bridges in the same highway corridor integrated in a cyber-physical systems (CPS) framework, and utilizing advanced computer vision algorithms, the authors have gathered a unique dataset consisting of pairs of bridge responses to the same truck load from live traffic moving across a 32.2 km (20 miles) stretch of the I-275 highway in southeast Michigan. Signal processing techniques have been employed to isolate the response of the bridges to a single truck load in a time series of recorded responses. Then, a deep-learning-based time series forecasting framework using the encoder-decoder architecture with gated recurrent unit (GRU) and long short-term memory (LSTM) cells has been used for bridge response forecasting. Baseline models based on linear time series models are also developed to which the deep-learning forecasting models can be compared. After training the models, it is observed that deep-learning-based models can accurately forecast the response of one bridge using the response of another and reduce the forecasting root-mean-squared error (RMSE) by at least 20% relative to baseline linear models. The forecasting capabilities of the encoder-decoder architecture proposed herein outperform traditional approaches to response forecasting. Trained versions of the encoderdecoder forecasting model

关键词： Time Series Forecasting Bridge Monitoring Encoder-Decoder Recurrent Neural Networks Deep Learning sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep-learning based Approach for Automatic Diacritization of Arabic Poems using sequence-to-sequence Model

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第1期14卷 42-46页

作者： Mahmoud, Mohamed S. Negied, Nermin Tech Univ Munich Sch Informat Munich Germany Sch Commun & Informat Engn Giza Egypt Nile Univ Sch Engn & Appl Sci Giza Egypt

Over the last 10 years, Arabic language have attracted researchers in the area of Natural Language Processing (NLP). A lot of research papers suddenly emerged in which the main work was the processing of Arabic language and its dialects too. Arabic language processing has been given a special name ANLP (Arabic Natural Language Processing). A lot of ANLP work can be found in literature including almost all NLP applications. Many researchers have been attracted also to Arabic linguistic knowledge. The work expands from Basic Language Analysis to Semantic Level Analysis. But Arabic text semantic analysis cannot be held without considering diacritization, which can greatly affect the meaning. Many Arabic texts are written without diacritization, and Diacritizing them manually is a very tiresome process that may need an expert. Automatic diacritization systems became a demand as an initial step for processing Arabic text for any Arabic Language Processing application as Arabic diacritization is very important to get a readable and understandable Arabic text. For this reason, many researchers recently worked on building systems and tools that automatically diacritize un-diacritized Arabic texts. This work presents a novel deep learning-based sequence -to-sequence model to diacritize un-diacritized Arabic poems. The proposed model was tested and achieved high diacritization accuracy rate.

关键词： Text diacritization deep learning sequence-to-sequence regex tokenization ANLP

来源：评论

学校读者我要写书评

暂无评论

Comparative study of sequence-to-sequence models:From RNNs to transformers

Comparative study of sequence-to-sequence models:From RNNs t...

引用

作者： Jiancong Zhu The Henry Samueli School of Engineering University of California

In this comprehensive exploration of sequence-to-sequence models in Natural Language Processing(NLP),we have traced the trajectory of their evolution and *** from foundational Recurrent Neural Networks(RNNs) to the revolutionary capabilities of Long Short-Term Memory(LSTM),In this comprehensive exploration of sequence-tosequence models in Natural Language Processing(NLP),we have meticulously traced the trajectory of their evolution and impactful *** the foundational Recurrent Neural Networks(RNNs) to the revolutionary capabilities of Long Short-Term Memory(LSTM),as well as the transformative innovations brought forth by Transformers and BERT,this review eloquently highlights the monumental advancements that have fundamentally reshaped our understanding and generation of *** crux of our comparative analysis lies in its ability to spotlight the distinctive strengths and limitations inherent in each *** an intricate examination,we uncover their nuanced applications across a diverse spectrum of NLP *** noteworthy is the pivotal role played by Transformers and the transformative Bidirectional Encoder Representations from Transformers(BERT).The paper concludes with a summary and outlook of the entire paper.

关键词： sequence-to-sequence Recurrent Neural Networks LSTMs Transformers

来源：评论

学校读者我要写书评

暂无评论

Non-parallel sequence-to-sequence Voice Conversion for Arbitrary Speakers 12

Non-parallel Sequence-to-Sequence Voice Conversion for Arbit...

引用

12th International Symposium on Chinese Spoken Language Processing (ISCSLP)

作者： Zhang, Ying Che, Hao Wang, Xiaorui Kwai Beijing Peoples R China

ISBN: (纸本)9781728169941

Voice conversion (VC) aims to modify the speaker's tone while preserving the linguistic information. Recent works show that voice conversion has made great progress on non-parallel data by introducing phonetic posteriorgrams (PPGs). However, once the prosody of source and target speaker differ significantly, it causes noticeable quality degradation of the converted speech. To alleviate the impact of the prosody of the source speaker, we propose a sequence-to-sequence voice conversion (Seq2Seq-VC) method, which utilizes connectionist temporal classification PPGs (CTC-PPGs) as inputs and models the non-linear length mapping between CTC-PPGs and frame-level acoustic features. CTC-PPGs are extracted by the CTC based automatic speech recognition (CTC-ASR) model and used to replace time-aligned PPGs. The blank token is introduced in CTC-ASR outputs to identify fewer information frames and get around consecutive repeating characters. After removing blank tokens, the left CTC-PPGs only contain linguistic information, and the phone duration information of the source speech is removed. Thus, phone durations of the converted speech are more faithful to the target speaker, which means higher similarity to the target and less interference from different source speakers. Experimental results show our Seq2Seq-VC model achieves higher scores in similarity and naturalness tests than the baseline method. What's more, we expand our seq2seq-VC approach to voice conversion towards arbitrary speakers with limited data. The experimental results demonstrate that our Seq2Seq-VC model can transfer to a new speaker using 100 utterances (about 5 minutes).

关键词： voice conversion sequence-to-sequence connectionist temporal classification limited data

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence AUTOMATIC SPEECH RECOGNITION WITH WORD EMBEDDING REGULARIZATION AND FUSED DECODING

SEQUENCE-TO-SEQUENCE AUTOMATIC SPEECH RECOGNITION WITH WORD ...

引用

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

作者： Liu, Alexander H. Sung, Tzu-Wei Chuang, Shun-Po Lee, Hung-yi Lee, Lin-shah Natl Taiwan Univ Coll Elect Engn & Comp Sci Taipei Taiwan Univ Calif San Diego Dept Comp Sci & Engn San Diego CA 92103 USA

ISBN: (纸本)9781509066315

In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the cosine similarity between a transformed decoder feature and the target word embedding. Based on the regularized decoder, we further proposed the fused decoding mechanism. This allows the decoder to consider the semantic consistency during decoding by absorbing the information carried by the transformed decoder feature, which is learned to be close to the target word embedding. Initial results on LibriSpeech demonstrated that pre-trained word embedding can significantly lower ASR recognition error with a negligible cost, and the choice of word embedding algorithms among Skip-gram, CBOW and BERT is important.

关键词： automatic speech recognition sequence-to-sequence word embedding regularization decoding

来源：评论

学校读者我要写书评

暂无评论

A short-term electric load forecast method based on improved sequence-to-sequence GRU with adaptive temporal dependence

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2022年 137卷 107627-107627页

作者： Li, Dan Sun, Guangfan Miao, Shuwei Gu, Yingzhong Zhang, Yuanhang He, Shuai China Three Gorges Univ Elect & New Energy Coll Yichang 443000 Peoples R China Chongqing Univ State Key Lab Power Transmiss Equipment & Syst Se Chongqing Peoples R China China Three Gorges Univ Hubei Prov Key Lab Operat & Control Cascade Hydro Yichang 443000 Peoples R China Google LLC 1600 Plymouth St Mountain View CA 94043 USA

Accurate and efficient short-term electric load forecast (STLF) is essential for power systems' reliable and economical operation. The temporal dependence of actual load exhibits dynamics and variability, while the current STLF methods often neglect it, resulting in poor robustness. This paper proposes an STLF method based on an improved sequence-to-sequence gated recurrent unit network (S2S-IGRU) to solve this problem, with a three-step adaptive framework for following dynamic temporal dependency pattern. In the first step, the maximum duration of the temporal dependence is estimated empirically based on the autocorrelation coefficient. It is set as the initial upper limit of the window length to construct the time series samples. In addition, a sine-cosine cycle encoder is used for the periodic categorical inputs. In the second step, an S2S-IGRU initialized with a Chrono initializer is used to forecast the load in upcoming days, which enables a flexible setting of the memory retention time. In the third step, the prediction error changing curve with window length is selected as a fine-tuning criterion to obtain the optimal length of the time window. The results from two real examples justify the proposed method of significantly improving forecast accuracy and adaptability on varied forecast horizons and load datasets with different temporal dynamic patterns.

关键词： Short-term load forecast Temporal dependence sequence-to-sequence Gated recurrent unit

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：