检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Mizuno, Saki Hojo, Nobukatsu Kobashikawa, Satoshi Masumura, Ryo Ntt Computer & Data Science Laboratories

ISBN: (纸本)9781728163277

We propose a method for next-speaker prediction, a task to predict who speaks in the next turn among multiple current listeners, in multi-party video conversation. Previous studies used non-verbal features, such as head movements and gaze behavior, for next-speaker prediction in face-to-face conversation. However, in video conversation, these non-verbal features are vague and ineffective because they look at the screen displaying other participants. Since non-verbal features include participant characteristics, it is necessary to use training data with rich combinations of participants to robustly predict the next speaker. Previous studies used training data with a limited number of combinations of participants because the data consist only of recorded data. Therefore, the proposed method uses 1) novel non-verbal features for next-speaker prediction in video conversation, specifically facial expressions, hand movements and speech segments, and 2) data augmentation of participant combinations in the training data. We conducted experiments to evaluate the proposed method, and the results using video-conversation data indicate its effectiveness. © 2023 IEEE.

关键词： multi-party conversation next-speaker prediction non-verbal information video conversation

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation 12

Recurrent Neural Networks for Learning Long-term Temporal De...

引用

12th IEEE International Conference on Big Knowledge, ICBK 2021

作者： Ohno, Kentaro Kumagai, Atsutoshi NTT Computer Data Science Laboratories Japan

ISBN: (纸本)9781665438582

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has recently been re-interpreted as a representative of the time scale of the state, i.e., a measure how long the RNN retains information on inputs. On the basis of this interpretation, several parameter initialization methods to exploit prior knowledge on temporal dependencies in data have been proposed to improve learn-ability. However, the interpretation relies on various unrealistic assumptions, such as that there are no inputs after a certain time point. In this work, we reconsider this interpretation of the forget gate in a more realistic setting. We first generalize the existing theory on gated RNNs so that we can consider the case where inputs are successively given. We then argue that the interpretation of a forget gate as a temporal representation is valid when the gradient of loss with respect to the state decreases exponentially as time goes back. We empirically demonstrate that existing RNNs satisfy this gradient condition at the initial training phase on several tasks, which is in good agreement with previous initialization methods. On the basis of this finding, we propose an approach to construct new RNNs that can represent a longer time scale than conventional models, which will improve the learnability for long-term sequential data. We verify the effectiveness of our method by experiments with real-world datasets. © 2021 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Logical entanglement distribution between distant 2D array qubits

arXiv

引用

arXiv 2025年

作者： Maeda, Yuya Suzuki, Yasunari Kobayashi, Toshiki Yamamoto, Takashi Tokunaga, Yuuki Fujii, Keisuke Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan NTT Computer and Data Science Laboratories NTT Corporation Musashino180-8585 Japan JST PRESTO 4-1-8 Honcho Kawaguchi Saitama332-0012 Japan Center for Quantum Information and Quantum Biology Institute for Open and Transdisciplinary Research Initiatives Osaka University Japan Center for Quantum Computing RIKEN Wako Saitama351-0198 Japan

Sharing logical entangled pairs between distant quantum nodes is a key process to achieve fault-tolerant quantum computation and communication. However, there is a gap between current experimental specifications and theoretical requirements for sharing logical entangled states while improving experimental techniques. Here, we propose an efficient logical entanglement distribution protocol based on surface codes for two distant 2D qubit array with nearest-neighbor interaction. A notable feature of our protocol is that it allows post-selection according to error estimations, which provides the tunability between the infidelity of logical entanglements and the success probability of the protocol. With this feature, the fidelity of encoded logical entangled states can be improved by sacrificing success rates. We numerically evaluated the performance of our protocol and the trade-off relationship, and found that our protocol enables us to prepare logical entangled states while improving fidelity in feasible experimental parameters. We also discuss a possible physical implementation using neutral atom arrays to show the feasibility of our protocol. © 2025, CC BY.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations 38

Fast Iterative Hard Thresholding Methods with Pruning Gradie...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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

We accelerate the iterative hard thresholding (IHT) method, which finds k important elements from a parameter vector in a linear regression model. Although the plain IHT repeatedly updates the parameter vector during the optimization, computing gradients is the main bottleneck. Our method safely prunes unnecessary gradient computations to reduce the processing time. The main idea is to efficiently construct a candidate set, which contains k important elements in the parameter vector, for each iteration. Specifically, before computing the gradients, we prune unnecessary elements in the parameter vector for the candidate set by utilizing upper bounds on absolute values of the parameters. Our method guarantees the same optimization results as the plain IHT because our pruning is safe. Experiments show that our method is up to 73 times faster than the plain IHT without degrading accuracy. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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 35

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

引用

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

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

ISBN: (纸本)9798350367041

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. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Learning Robust Convolutional Neural Networks with Relevant Feature Focusing Via Explanations

Learning Robust Convolutional Neural Networks with Relevant ...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Adachi, Kazuki Yamaguchi, Shin'ya Ntt Corporation Computer and Data Science Laboratories Japan

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Existing image recognition techniques based on convolutional neural networks (CNNs) basically assume that the training and test datasets are sampled from i.i.d distributions. However, this assumption is easily broken in the real world because of the distribution shift that occurs when the co-occurrence relations between objects and backgrounds in input images change. Under this type of distribution shift, CNNs learn to focus on features that are not task-relevant, such as backgrounds from the training data, and degrade their accuracy on the test data. To tackle this problem, we propose relevant feature focusing (ReFF). ReFF detects task-relevant features and regularizes CNNs via explanation outputs (e.g., Grad-CAM). Since ReFF is composed of post-hoc explanation modules, it can be easily applied to off-the-shelf CNNs. Furthermore, ReFF requires no additional inference cost at test time because it is only used for regularization while training. We demonstrate that CNNs trained with ReFF focus on features relevant to the target task and that ReFF improves the test-time accuracy. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TRANSFERRING LEARNING TRAJECTORIES OF NEURAL NETWORKS 12

TRANSFERRING LEARNING TRAJECTORIES OF NEURAL NETWORKS

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Chijiwa, Daiki NTT Computer and Data Science Laboratories NTT Corporation Japan

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one (named learning transfer problem) and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training, and can be trained significantly faster than training from scratch. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Text-to-Text Pre-Training with Paraphrasing for Improving Transformer-based Image Captioning 31

Text-to-Text Pre-Training with Paraphrasing for Improving Tr...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Masumura, Ryo Makishima, Naoki Ihori, Mana Takashima, Akihiko Tanaka, Tomohiro Orihashi, Shota NTT Computer Data Science Laboratories NTT Corporation Japan

ISBN: (纸本)9789464593600

In this paper, we propose a novel training method for the transformer encoder-decoder based image captioning, which directly generates a captioning text from an input image. In general, many image-to-text paired datasets need to be prepared for robust image captioning, but such datasets cannot be collected in practical cases. Our key idea for mitigating the data preparation cost is to utilize text-to-text paraphrasing modeling, i.e., a task to convert an input text into different expressions without changing the meaning. In fact, paraphrasing deals with a similar transformation task to image captioning even though paraphrasing tasks have to handle texts instead of images. In our proposed method, an encoder-decoder network trained via the paraphrasing task is directly leveraged for image captioning. Thus, an encoder-decoder network pre-trained by a text-to-text transformation task is transferred into an image-to-text transformation task even though a different modal must be handled in the encoder network. Our experiments using the MS COCO caption datasets demonstrate the effectiveness of the proposed method. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Quantigraphic Image Enhancement via Comparametric Equations 48

Deep Quantigraphic Image Enhancement via Comparametric Equat...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Xiaomeng Sun, Yongqing Kimura, Akisato Ntt Corporation Communication Science Laboratories Japan Ntt Corporation Computer and Data Science Laboratories Japan

ISBN: (纸本)9781728163277

Most recent methods of deep image enhancement can be generally classified into two types: decompose-and-enhance and illumination estimation-centric. The former is usually less efficient, and the latter is constrained by a strong assumption regarding image reflectance as the desired enhancement result. To alleviate this constraint while retaining high efficiency, we propose a novel trainable module that diversifies the conversion from the low-light image and illumination map to the enhanced image. It formulates image enhancement as a comparametric equation parameterized by a camera response function and an exposure compensation ratio. By incorporating this module in an illumination estimation-centric DNN, our method improves the flexibility of deep image enhancement, limits the computational burden to illumination estimation, and allows for fully unsupervised learning adaptable to the diverse demands of different tasks. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Toward data Efficient Model Merging between Different datasets without Performance Degradation 16

Toward Data Efficient Model Merging between Different Datase...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Yamada, Masanori Yamashita, Tomoya Yamaguchi, Shin’ya Chijiwa, Daiki NTT Social Informatics Laboratories Japan NTT Computer and Data Science Laboratories Japan

Model merging is attracting attention as a novel method for creating a new model by combining the weights of different trained models. While previous studies reported that model merging works well for models trained on a single dataset with different random seeds, model merging between different datasets remains unsolved. In this paper, we attempt to reveal the difficulty in merging such models trained on different datasets and alleviate it. Our empirical analyses show that, in contrast to the single-dataset scenarios, dataset information needs to be accessed to achieve high accuracy when merging models trained on different datasets. However, the requirement to use full datasets not only incurs significant computational costs but also becomes a major limitation when integrating models developed and shared by others. To address this, we demonstrate that dataset reduction techniques, such as coreset selection and dataset condensation, effectively reduce the data requirement for model merging. In our experiments with SPLIT-CIFAR10 model merging, the accuracy is significantly improved by 31% when using the full dataset and 24% when using the sampled subset compared with not using the dataset. Our code is available at this URL. © 2024 M. Yamada, T. Yamashita, S. Yamaguchi & D. Chijiwa.

关键词： data accuracy

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：