检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Ramponi, Giorgia Kolev, Pavel Laurière, Mathieu Pietquin, Olivier Geist, Matthieu He, Niao ETH AI Center Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany Google DeepMind ETH Zurich Department of Computer Science Switzerland Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning NYU Shanghai China

ISBN: (纸本)9781713899921

We explore the problem of imitation learning (IL) in the context of mean-field games (MFGs), where the goal is to imitate the behavior of a population of agents following a Nash equilibrium policy according to some unknown payoff function. IL in MFGs presents new challenges compared to single-agent IL, particularly when both the reward function and the transition kernel depend on the population distribution. In this paper, departing from the existing literature on IL for MFGs, we introduce a new solution concept called the Nash imitation gap. Then we show that when only the reward depends on the population distribution, IL in MFGs can be reduced to single-agent IL with similar guarantees. However, when the dynamics is population-dependent, we provide a novel upper-bound that suggests IL is harder in this setting. To address this issue, we propose a new adversarial formulation where the reinforcement learning problem is replaced by a mean-field control (MFC) problem, suggesting progress in IL within MFGs may have to build upon MFC. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Population distribution

来源：评论

学校读者我要写书评

暂无评论

System Methodology of Data Analysis and Preprocessing for Solving Classification Problems

System Methodology of Data Analysis and Preprocessing for So...

引用

International computer sciences and Information Technologies (CSIT)

作者： Irina Kalinina Aleksandr Gozhyj Victoria Vysotska Eugene Malakhov Victor Gozhyj Iryna Tregubova Intelligent Information Systems Department Petro Mohyla Black Sea National University Mykolayiv Ukraine Department of Information Systems and Networks Institute of Computer Science and Information Technologies National University “Lviv Polytechnic” Lviv Ukraine Department of Mathematical Methods of Computer Systems of Odessa National Mechnikov University Odesa Ukraine Department of Computer Science State University of Intelligent Technologies and Telecommunications Odesa Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The article describes and investigates the systematic methodology of data analysis and preprocessing for solving classification problems. The methodology combines the following groups of methods on the basis of a systemic approach: methods of processing data gaps, methods of processing anomalous values, methods of feature generation, methods of identifying nonlinearities and non-stationarity, and normalization methods. Methods of character generation were studied. Methods of feature selection and generation are divided into three main groups: filtering methods, wrapping methods, and embedded methods. Since feature selection plays a crucial role in machine learning, increasing model performance and reducing computational costs, the paper proposes a combined feature selection method that includes the step-by-step use of both filtering and wrapping methods. The method consists of five steps to efficiently select the most relevant features of a data set. It offers a better approach to feature selection. This results in improved model performance with fewer features and reduced computational cost. The creation of a red wine classification system was considered for the experimental verification of the system methodology of analysis and pre-processing of data. The Red Wine Quality dataset was used. The purpose of the classification is to identify factors associated with the risk of untimely delivery of previous orders to customers and information about recipients of goods. To solve the task of wine quality classification, simulations were carried out using various algorithms. The effectiveness of the system approach to solving problems of analysis and preprocessing of data to solve problems of classification was proved.

关键词： Data analysis Systematics Filtering Computational modeling Machine learning Feature extraction Computational efficiency Classification algorithms Wrapping Information technology

来源：评论

学校读者我要写书评

暂无评论

Indonesian-Sundanese Language Machine Translation using Bidirectional Long Short-term Memory Model

Indonesian-Sundanese Language Machine Translation using Bidi...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of two models: the Long Short-term Memory and the Bidirectional Long Short-term Memory models as machine language translation models involving Bahasa Indonesia and the Sundanese language. The empiric results showed that the Bidirectional Long Short-term Memory model achieves higher performance as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.95 and 0.95 average training accuracy respectively;and 0.90 and 0.89 average testing BLEU scores respectively) than the Long Short-term Memory model as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.93 and 0.92 average training accuracy respectively;and 0.91 and 0.88 average testing BLEU scores). These results validate some previously reported studies that claim the Bidirectional Long Short-term Memory model potentially outperform the Long Short-term Memory model when it is used to process a sequence dataset. © 2023 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Revalidating the Encoder-Decoder Depths and Activation Function to Find Optimum Vanilla Transformer Model

Revalidating the Encoder-Decoder Depths and Activation Funct...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota Bina Nusantara University Graduate Program- Computer Science Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University Online Learning Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The transformer model has become a state-of-the-art model in Natural Language Processing. The initial transformer model, known as the vanilla transformer model, is designed to improve some prominent models in sequence modeling and transduction problems such as language modeling and machine translation. The initial transformer model has 6 stacks of identical encoder-decoder layers with an attention mechanism whose aim is to push limitations of common recurrent language models and encoder-decoder architectures. Its outstanding performance has inspired many researchers to extend the architecture to improve its performance and computation efficiency. Despite many extensions to the vanilla transformer, there is no clear explanation of the encoder-decoder set out depth in the vanilla transformer model. This paper presents exploration results on the effect of combination encoder-decoder layer depth and activation function in the feed-forward layer of the vanilla transformer model on its performance. The model is tested to address a downstream task: text translation from Bahasa Indonesia to the Sundanese language. Although the value difference is not significantly large, the empirical results show that the combination of depth = 2 with Sigmoid, Tanh, and ReLU activation function;and d = 6 with ReLU activation shows the highest average training accuracy. Interestingly, d = 6 and ReLU show the lowest average training and validation loss. However, statistically, there is no significant difference between depth and activation functions. © 2023 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision 29

Speaker Clustering in Textual Dialogue with Pairwise Utteran...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Su, Zhihua Zhou, Qiang State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China Beijing National Research Center for Information Science and Technology Tsinghua University China

We propose a speaker clustering model for textual dialogues, which groups the utterances of a multi-party dialogue without speaker annotations, so that the actual speakers are identical inside each cluster. We find that, without knowing the speakers, the interactions between utterances are still implied in the text, which suggest the relations between speakers. In this work, we model the semantic content of utterance with a pre-trained language model, and the relations between speakers with an utterance-level pairwise matrix. The semantic content representation can be further instructed by cross-corpus dialogue act modeling. The speaker labels are finally generated by spectral clustering. Experiments show that our model outperforms the sequence classification baseline, and benefits from the auxiliary dialogue act classification task. We also discuss the detail of determining the number of speakers (clusters), eliminating the interference caused by semantic similarity, and the impact of utterance distance. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Start State Selection for Control Policy Learning from Optimal Trajectories

Start State Selection for Control Policy Learning from Optim...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Christoph Zelch Jan Peters Oskar von Stryk Department of Computer Science TU Darmstadt Simulation Systems Optimization and Robotics Group Darmstadt Germany Department of Computer Science Intelligent Autonomous Systems Group TU Darmstadt Darmstadt Germany

Combination of optimal control methods and machine learning approaches allows to profit from complementary benefits of each field in control of robotic systems. Data from optimal trajectories provides valuable information that can be used to learn a near-optimal state-dependent feedback control policy. To obtain high-quality learning data, careful selection of optimal trajectories, determined by a set of start states, is essential to achieve a good learning performance. In this paper, we extend previous work with new comple-menting strategies to generate start points. These methods complement the existing approach, as they introduce new criteria to identify relevant regions in joint state space that need coverage by new trajectories. It is demonstrated that the extensions significantly improve the overall performance of the previous method in simulation on full nonlinear dynamics model of the industrial Manutec r3 robot arm. Further, it is demonstrated that it suffices to learn a policy that reaches the proximity of the goal state, from where a PI controller can be used for stable control reaching the final system state.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Inference at the Edge: A Batch Processing Approach

Hierarchical Inference at the Edge: A Batch Processing Appro...

引用

IEEE/ACM Symposium on Edge Computing (SEC)

作者： Afroditi Letsiou Vishnu Narayanan Moothedath Adarsh Prasad Behera Jaya Prakash Champati James Gross Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Computer Science University of Victoria British Columbia Canada

ISBN: (数字)9798350378283

ISBN: (纸本)9798350378290

Deep learning (DL) applications have rapidly evolved to address increasingly complex tasks by leveraging large-scale, resource-intensive models. However, deploying such models on low-power devices is not practical or economically scalable. While cloud-centric solutions satisfy these computational demands, they present challenges in terms of communication costs and latencies for real-time applications when every computation task is offloaded. To mitigate these concerns, hierarchical inference (HI) frameworks have been proposed, enabling edge devices equipped with small ML models to collaborate with edge servers by selectively offloading complex tasks. Existing HI approaches depend on immediate offloading of data upon selection, which can lead to inefficiencies due to frequent communication, especially in time-varying wireless environments. In this work, we introduce Batch HI, an approach that offloads samples in batches, thereby reducing communication overhead and improving system efficiency while achieving similar performance as existing HI methods. Additionally, we find the optimal batch size that attains a crucial balance between responsiveness and system time, tailored to specific user requirements. Numerical results confirm the effectiveness of our approach, highlighting the scenarios where batching is particularly beneficial.

关键词： Wireless communication Costs Computational modeling Biological system modeling Probabilistic logic Linear programming Real-time systems Time factors Servers Optimization

来源：评论

学校读者我要写书评

暂无评论

Selecting a Robotic Platform for Education

Selecting a Robotic Platform for Education

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Evripidou, Salomi Doitsidis, Lefteris Tsinarakis, George Zinonos, Zinon Chatzichristofis, Savvas A. Neapolis University Pafos Intelligent Systems Lab Department of Computer Science Pafos Cyprus School of Production Engineering Management Technical University of Crete Chania Greece

ISBN: (纸本)9781665441544

Undoubtedly, the popularity of educational robotic platforms has disrupted the way students are educated while forming an important and promising new market for robotics and consumer electronics companies. Selecting a robotic platform for education is an important task, as it can affect the learning process and the respective learning outcome. To effectively select a robotic kit for a specific activity, several factors should be taken into account. However, choosing a robot for one particular application has become more complicated in recent years because of the increased complexity and the available features and facilities constantly introduced into the robots. Despite the fact that several robot selection methodologies have been established for industrial uses, there has been little study on robot selection for learning purposes. The main objective of this work is to determine the most important parameters for selecting a robotic platform, as they were identified through an extensive literature survey. The work aims to assist consumers in choosing the appropriate educational robots, while supporting manufacturers in designing platforms suitable for education purposes. © 2022 IEEE.

关键词： Educational robots

来源：评论

学校读者我要写书评

暂无评论

Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On

Cloth2Tex: A Customized Cloth Texture Generation Pipeline fo...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Daiheng Gao Xu Chen Xindi Zhang Qi Wang Ke Sun Bang Zhang Liefeng Bo Qixing Huang Alibaba XR Lab Department of Computer Science ETH Zurich Max Planck Institute for Intelligent Systems The University of Texas at Austin

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Fabricating and designing 3D garments has become extremely demanding with the increasing need for synthesizing realistic dressed persons for a variety of applications, e.g. 3D virtual try-on, digitalization of 2D clothes into 3D apparel, and cloth animation. It thus necessitates a simple and straightforward pipeline to obtain high-quality texture from simple input, such as 2D reference images. Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process. We propose a novel method, called Cloth2Tex, which eliminates the human burden in this process. Cloth2Tex is a self-supervised method that generates texture maps with reasonable layout and structural consistency. Another key feature of Cloth2Tex is that it can be used to support high-fidelity texture inpainting. This is done by combining Cloth2Tex with a prevailing latent diffusion model. We evaluate our approach both qualitatively and quantitatively and demonstrate that Cloth2Tex can generate high-quality texture maps and achieve the best visual effects in comparison to other methods. For more details and animated results, please see https://tomguluson92. ***/projects/cloth2tex/.

关键词： Training Three-dimensional displays Pipelines Clothing Layout Process control Manuals

来源：评论

学校读者我要写书评

暂无评论

ROVER: A Multi-Season Dataset for Visual SLAM

arXiv

引用

arXiv 2024年

作者： Schmidt, Fabian Blessing, Constantin Enzweiler, Markus Valada, Abhinav The Institute for Intelligent Systems Esslingen University of Applied Sciences Esslingen Germany The Department of Computer Science University of Freiburg Freiburg Germany

Robust Simultaneous Localization and Mapping (SLAM) is a crucial enabler for autonomous navigation in natural, unstructured environments such as parks and gardens. However, these environments present unique challenges for SLAM due to frequent seasonal changes, varying light conditions, and dense vegetation. These factors often degrade the performance of visual SLAM algorithms originally developed for structured urban environments. To address this gap, we present ROVER, a comprehensive benchmark dataset tailored for evaluating visual SLAM algorithms under diverse environmental conditions and spatial configurations. We captured the dataset with a robotic platform equipped with monocular, stereo, and RGB-D cameras, as well as inertial sensors. It covers 39 recordings across five outdoor locations, collected through all seasons and various lighting scenarios, i.e., day, dusk, and night with and without external lighting. With this novel dataset, we evaluate several traditional and deep learning-based SLAM methods and study their performance in diverse challenging conditions. The results demonstrate that while stereo-inertial and RGB-D configurations generally perform better under favorable lighting and moderate vegetation, most SLAM systems perform poorly in low-light and high-vegetation scenarios, particularly during summer and autumn. Our analysis highlights the need for improved adaptability in visual SLAM algorithms for outdoor applications, as current systems struggle with dynamic environmental factors affecting scale, feature extraction, and trajectory consistency. This dataset provides a solid foundation for advancing visual SLAM research in real-world, natural environments, fostering the development of more resilient SLAM systems for long-term outdoor localization and mapping. The dataset and the code of the benchmark are available under https://***/rover. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

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：