检索结果-内蒙古大学图书馆

Fast Sparse Modeling Technology Opening Up the Future with Ultra-high-dimensional data

ntt Technical Review 2023年第6期21卷 12-16页

作者： Ida, Yasutoshi NTT Computer and Data Science Laboratories

As one pillar of ntt’s IOWN (Innovative Optical and Wireless Network) vision, Digital Twin Computing aims to construct the world in a digital space. To this end, it is essential that data be obtained from people and things by sensors. However, advances in sensing technologies have created a new issue in which an increase in the number of data dimensions makes processing time longer, which makes it difficult to analyze and use collected data within a realistic period of time. We asked ntt Distinguished Researcher Yasutoshi Ida to tell us about "fast sparse modeling technology" as a means of solving this problem. © 2023 Nippon Telegraph and Telephone Corp.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Meta-learning for Positive-unlabeled Classification

arXiv

引用

arXiv 2024年

作者： Kumagai, Atsutoshi Iwata, Tomoharu Fujiwara, Yasuhiro NTT Computer and Data Science Laboratories Japan NTT Communication Science Laboratories Japan

We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target tasks. PU learning is an important problem since PU data naturally arise in real-world applications such as outlier detection and information retrieval. Existing PU learning methods require many PU data, but sufficient data are often unavailable in practice. The proposed method minimizes the test classification risk after the model is adapted to PU data by using related tasks that consist of positive, negative, and unlabeled data. We formulate the adaptation as an estimation problem of the Bayes optimal classifier, which is an optimal classifier to minimize the classification risk. The proposed method embeds each instance into a task-specific space using neural networks. With the embedded PU data, the Bayes optimal classifier is estimated through density-ratio estimation of PU densities, whose solution is obtained as a closed-form solution. The closed-form solution enables us to efficiently and effectively minimize the test classification risk. We empirically show that the proposed method outperforms existing methods with one synthetic and three real-world datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Talking Face Generation for Impression Conversion Considering Speech Semantics

Talking Face Generation for Impression Conversion Considerin...

引用

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

作者： Saki Mizuno Nobukatsu Hojo Kazutoshi Shinoda Keita Suzuki Mana Ihori Hiroshi Sato Tomohiro Tanaka Naotaka Kawata Satoshi Kobashikawa Ryo Masumura NTT Computer & Data Science Laboratories NTT Corporation Japan

This study investigates the talking face generation method to convert a speaker’s video to give a target impression, such as “favorable” or “considerate”. Such an impression conversion method needs to consider the input speech semantics because they affect the impression of a speaker’s video along with the facial expression. Conventional emotional talking face generation methods utilize speech information to synchronize the lip and speech of the output video. However, they cannot consider speech semantics because the speech representations contain only phonetic information. To solve this problem, we propose a facial expression conversion model that uses a semantic vector obtained from BERT embeddings of speech recognition results of input speech. We first constructed an audio-visual dataset with impression labels assigned to each utterance. The evaluation results based on the dataset showed that the proposed method could improve the estimation accuracy of the facial expressions of the target video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Acoustic XR Technology Merging Real and Virtual Sounds

引用

ntt Technical Review 2024年第6期22卷 30-34页

作者： Noguchi, Kenichi Chiba, Hironobu Kako, Tatsuya Kozuka, Shihori Kurokawa, Yoshiaki Watanabe, Yuki Nakayama, Akira Ultra-Reality Computing Group NTT Computer and Data Science Laboratories

With the spread of open-ear earphones that do not cover the ear, new listening experiences are being proposed that combines real ambient sounds with virtual sounds heard from earphones. At ntt, we call this merging of the real and virtual sounds through open-ear earphones "acoustic XR (extended reality) technology," which we are now developing with a view to actual services. In this article, we describe this technology with a focus on actual trials and touch upon future developments. © 2024 Nippon Telegraph and Telephone Corp.. All rights reserved.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models

arXiv

引用

arXiv 2025年

作者： Chijiwa, Daiki Hasegawa, Taku Nishida, Kyosuke Saito, Kuniko Takeuchi, Susumu NTT Computer and Data Science Laboratories NTT Corporation Japan NTT Human Informatics Laboratories NTT Corporation Japan

While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability. Thus the underlying foundation model should be eventually replaced by new ones, which leads to repeated cost of fine-tuning these new models. Existing work addresses this problem by inference-time tuning, i.e., modifying the output probabilities from the new foundation model with the outputs from the old foundation model and its fine-tuned model, which involves an additional overhead in inference by the latter two models. In this paper, we propose a new fine-tuning principle, Portable Reward Tuning (PRT), that reduces the inference overhead by its nature, based on the reformulation of fine-tuning as the reward maximization. Specifically, instead of fine-tuning parameters of the foundation models, PRT trains the reward model explicitly through the same loss function as in fine-tuning. During inference, the reward model can be used with any foundation model (with the same set of vocabularies or labels) through the formulation of reward maximization. Experimental results, covering both vision and language models, demonstrate that the PRT-trained model can achieve comparable accuracy to the existing work of inference-time tuning, with less inference cost. Copyright © 2025, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Discovering Implicit Operational Knowledge by Identifying Business Processes that Involve Multiple Organizational Entities

Discovering Implicit Operational Knowledge by Identifying Bu...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Shinobu Saito Yukako Iimura NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

One of the success factors of Business process outsourcing (BPO) is a comprehensive and in-depth understanding of the business processes outsourced. However, such business processes are often undocumented, and discovering them is difficult and time-consuming for BPO service providers. Previously, we introduced an approach for business process discovery that uses swim lanes to recognize that different parts of the process may be performed by different parts of an organization. It generates the business process from an event log and user information extracted from an existing system. Herein, this paper examines whether the approach aids engineers and consultants in the providers who need to investigate business processes of organizations (i.e., their customers on which they do not have sufficient knowledge) discovering the implicit operational knowledge of the target business processes (e.g., undocumented local rules). To do so, we survey an industrial workflow system from which we collected data about 2,000 events and 269 users for a two-year period of the system's operation. We conducted a study on the case by means of document evaluation and expert interviews. The study suggested that the output of the approach is a valuable process visualization for identifying knowledge that is not documented nor recognized by even experts in organizations.

关键词： Knowledge engineering Surveys data visualization Organizations Manuals Software Outsourcing

来源：评论

学校读者我要写书评

暂无评论

Coding and Debugging by Separating Secret Code Toward Secure Remote Development 23

Coding and Debugging by Separating Secret Code Toward Secure...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

作者： Shinobu Saito NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (纸本)9798350329964

It is a higher priority for organizations to keep their source code secured. When a certain specific code includes a secret such as intellectual property, they need to pay special attention to prevent the secret code from leaking outside. On the other hand, sometimes code leaks comes from acts by inside programmers. This industrial paper proposes a MORDEn (Micro Organized Remote Development Environment) toward preventing code leaks. MORDEn enables programmers capable of coding and debugging by physically separating secret code from their client. We also introduce a showcase that demonstrates the feasibility of MORDEn from a case study project using it.

关键词： remote development environment

来源：评论

学校读者我要写书评

暂无评论

Towards N-version Quantum Software Systems for Reliable Classical-Quantum Computing

Towards N-version Quantum Software Systems for Reliable Clas...

引用

IEEE International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Shinobu Saito Suguru Endo Yasunari Suzuki NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (数字)9798350367041

ISBN: (纸本)9798350367058

While quantum computers have attracted much attention, dealing with computational errors due to noise effects caused by the interaction between quantum hardware and the external environment is a significant challenge. In this paper, we propose an approach to apply N-version programming (NVP) to quantum software to improve the reliability of the entire quantum software system. First, we define architecture patterns for N-version quantum software systems (NVQS) based on a combination of quantum libraries and devices. Next, given that the output of the quantum software system is a probability distribution, we came up with an evaluation strategy inspired by the concept of NVP for clustering and selecting multiple probability distributions output from NVQS. Finally, we outline our future experimental plan.

关键词： Quantum computing Conferences Noise Programming Software systems Reliability engineering Probability distribution Libraries Hardware Software reliability

来源：评论

学校读者我要写书评

暂无评论

Moiré Reduction Method for Visually Equivalent Light Field Display Using Special Barrier Aperture Structure 29

Moiré Reduction Method for Visually Equivalent Light Field ...

引用

29th International Display Workshops, IDW 2022

作者： Date, Munekazu Mitasaki, Tokinobu Matsumoto, Ayumi Kitahara, Masaki NTT Computer and Data Science Laboratories Nippon Telegraph and Telephone Corporation Japan

A visually equivalent light field 3D (VELF3D) display is a parallax-barrier-type autostereoscopic 3D display. Since stripes of the barrier and pixels are in parallel, moiré occurred, when the barrier is placed on the screen. In this paper, we suppressed moiré by only providing unevenness in the aperture shape of the barrier. © 2022 ITE and SID.

关键词： Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithm for K-Multiple-Means

引用

Proceedings of the ACM on Management of data 2024年第1期2卷 1-26页

作者： Yasuhiro Fujiwara Atsutoshi Kumagai Yasutoshi Ida Masahiro Nakano Makoto Nakatsuji Akisato Kimura NTT Communication Science Laboratories Atsugi-shi Kanagawa Japan NTT Computer and Data Science Laboratories Musashino-shi Tokyo Japan NTT Human Informatics Laboratories Yokosuka-shi Kanagawa Japan

K-Multiple-Means is an extension of K-means for the clustering of multiple means used in many applications, such as image segmentation, load balancing, and blind-source separation. Since K-means uses only one mean to represent each cluster, it fails to capture non-spherical cluster structures of data points. However, since K-Multiple-Means represents the cluster by computing multiple means and grouping them into specified c clusters, it can effectively capture the non-spherical clusters of the data points. To obtain the clusters, K-Multiple-Means updates a similarity matrix of a bipartite graph between the data points and the multiple means by iteratively computing the leading c singular vectors of the matrix. K-Multiple-Means, however, incurs a high computation cost for large-scale data due to the iterative SVD computations. Our proposal, F-KMM, increases the efficiency of K-Multiple-Means by computing the singular vectors from a smaller similarity matrix between the multiple means obtained from the similarity matrix of the bipartite graph. To compute the similarity matrix of the bipartite graph efficiently, we skip unnecessary distance computations and estimate lower bounding distances between the data points and the multiple means. Theoretically, the proposed approach guarantees the same clustering results as K-Multiple-Means since it can exactly compute the singular vectors from the similarity matrix between the multiple means. Experiments show that our approach is several orders of magnitude faster than previous clustering approaches that use multiple means.

关键词： algorithm clustering efficient

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：