检索结果-内蒙古大学图书馆

computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Yi Ken Chuah Chean Khim Toa Sim Kuan Goh Chow-Khuen Chan Hiroki Takada School of Electrical Engineering and Artificial Intelligence Xiamen University Malaysia Selangor Malaysia School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia Department of Biomedical Engineering Faculty of Engineering Universiti Malaya Malaysia Department of Human & Artificial Intelligent Systems Graduate School of Engineering University of Fukui Fukui Japan

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

In the Emotion research, there has been extensive work on emotion classification using electroencephalogram (EEG) signals. Despite most studies having achieved high accuracy, there is a potential for improvement in the model, particularly in training time reduction to optimize the modeling efficiency. Hence, our study aims to develop an efficient EEG-based emotion classification model that achieves high accuracy with a reduced number of training epochs. The proposed model, named EmoSense, employs a hybrid deep learning neural network architecture, which comprises a combination of Convolutional Neural Network (CNN), Deep Autoencoder (DAE), Bidirectional Long Short-Term Memory (BiLSTM), and an Attention mechanism. EEG features are first extracted using Differential Entropy (DE) on the EEG channels, which are then structured to form a four-dimensional (4D) representation of features with temporal, spatial, and frequency information. Subsequently, the extracted features will be used as input to the proposed model for training. Experimental evaluation of the publicly available DEAP dataset demonstrated that the proposed model achieved an accuracy of 94.11% with only 35 epochs. This performance is comparable with the result of the Cascaded Convolutional Recurrent Neural Networks model developed by Meng et al., which reported an accuracy of 94.64% with 100 epochs. The primary reason for the comparison with Meng et al. is that our overall process, including feature extraction and formation, is similar to their study, with the only difference being the deep learning architecture. Our finding indicates that the EmoSense model is not only able to achieve comparable accuracy but also reduces the number of training epochs, demonstrating the potential to learn the EEG features in a shorter time and lowering the computational cost. This study will benefit EEG-based emotion recognition to be more accessible and practical for real-world applications.

关键词： Training Emotion recognition Accuracy Attention mechanisms Computational modeling Brain modeling Feature extraction Electroencephalography Convolutional neural networks Tuning

来源：评论

学校读者我要写书评

暂无评论

ChatGPT4PCG Competition: Character-like Level Generation for science Birds

arXiv

引用

arXiv 2023年

作者： Taveekitworachai, Pittawat Abdullah, Febri Dewantoro, Mury F. Thawonmas, Ruck Togelius, Julian Renz, Jochen Graduate School of Information Science and Engineering Ritsumeikan University Kusatsu Japan College of Information Science and Engineering Ritsumeikan University Kusatsu Japan NYU Tandon School of Engineering New York University New York United States School of Computing The Australian National University Canberra Australia

This paper presents the first ChatGPT4PCG Competition at the 2023 IEEE Conference on Games. The objective of this competition is for participants to create effective prompts for ChatGPT-enabling it to generate science Birds levels with high stability and character-like qualities-fully using their creativity as well as prompt engineering skills. ChatGPT is a conversational agent developed by OpenAI. science Birds is selected as the competition platform because designing an Angry Birds-like level is not a trivial task due to the in-game gravity;the quality of the levels is determined by their stability. To lower the entry barrier to the competition, we limit the task to the generation of capitalized English alphabetical characters. We also allow only a single prompt to be used for generating all the characters. Here, the quality of the generated levels is determined by their stability and similarity to the given characters. A sample prompt is provided to participants for their reference. An experiment is conducted to determine the effectiveness of several modified versions of this sample prompt on level stability and similarity by testing them on several characters. To the best of our knowledge, we believe that ChatGPT4PCG is the first competition of its kind and hope to inspire enthusiasm for prompt engineering in procedural content generation. © 2023, CC BY.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data

arXiv

引用

arXiv 2024年

作者： Fang, Xiang Easwaran, Arvind Genest, Blaise Suganthan, Ponnuthurai Nagaratnam Interdisciplinary Graduate Programme Energy Research Institute NTU Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore CNRS France CNRS@CREATE IPAL IRL 2955 Singapore KINDI Computing Research Center College of Engineering Qatar University Doha Qatar

Out-of-distribution detection (OOD detection) aims to detect test samples drawn from a distribution that is different from the training distribution, in order to prevent models trained on in-distribution (ID) data from providing unavailable outputs. Current OOD detection systems typically refer to a single-domain class-balanced assumption that both the training and testing sets belong to the same domain and each class has the same size. Unfortunately, most real-world datasets contain multiple domains and class-imbalanced distributions, which severely limits the applicability of existing works. Previous OOD detection systems only focus on the semantic gap between ID and OOD samples. Besides the semantic gap, we are faced with two additional gaps: the domain gap between source and target domains, and the class-imbalance gap between different classes. In fact, similar objects from different domains should belong to the same class. In this paper, we introduce a realistic yet challenging setting: class-imbalanced cross-domain OOD detection (CCOD), which contains a well-labeled (but usually small) source set for training and conducts OOD detection on an unlabeled (but usually larger) target set for testing. We do not assume that the target domain contains only OOD classes or that it is class-balanced: the distribution among classes of the target dataset need not be the same as the source dataset. To tackle this challenging setting with an OOD detection system, we propose a novel uncertainty-aware adaptive semantic alignment (UASA) network based on a prototype-based alignment strategy. Specifically, we first build label-driven prototypes in the source domain and utilize these prototypes for target classification to close the domain gap. Rather than utilizing fixed thresholds for OOD detection, we generate adaptive sample-wise thresholds to handle the semantic gap. Finally, we conduct uncertainty-aware clustering to group semantically similar target samples to relieve the c

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Learning Soft Robot Dynamics using Differentiable Kalman Filters and Spatio-Temporal Embeddings

arXiv

引用

arXiv 2023年

作者： Liu, Xiao Ikemoto, Shuhei Yoshimitsu, Yuhei Amor, Heni Ben The School of Computing and Augmented Intelligence Arizona State University United States Department of Human Intelligence Systems Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Japan

This paper introduces a novel approach for modeling the dynamics of soft robots, utilizing a differentiable filter architecture. The proposed approach enables end-to-end training to learn system dynamics, noise characteristics, and temporal behavior of the robot. A novel spatio-temporal embedding process is discussed to handle observations with varying sensor placements and sampling frequencies. The efficacy of this approach is demonstrated on a tensegrity robot arm by learning end-effector dynamics from demonstrations with complex bending motions. The model is proven to be robust against missing modalities, diverse sensor placement, and varying sampling rates. Additionally, the proposed framework is shown to identify physical interactions with humans during motion. The utilization of a differentiable filter presents a novel solution to the difficulties of modeling soft robot dynamics. Our approach shows substantial improvement in accuracy compared to state-of-the-art filtering methods, with at least a 24% reduction in mean absolute error (MAE) observed. Furthermore, the predicted end-effector positions show an average MAE of 25.77mm from the ground truth, highlighting the advantage of our approach. The code is available at https: //***/ir-lab/soft_robot_DEnKF. © 2023, CC BY.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Fang, Xiang Easwaran, Arvind Genest, Blaise Suganthan, Ponnuthurai Nagaratnam Nanyang Technological University Energy Research Institute @ NTU Interdisciplinary Graduate Programme Singapore Nanyang Technological University College of Computing and Data Science Singapore CNRS@CREATE Singapore CNRS and CNRS@CREATE IPAL IRL 2955 France CNRS and CNRS@CREATE IPAL IRL 2955 Singapore Qatar University KINDI Computing Research Center College of Engineering Doha Qatar

This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have had decent success, they are ineffective for real-world challenging applications since these methods regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, 'cat' on CIFAR-10 and 'tabby cat' on Tiny-ImageNet share the same semantics but have different labels due to various label granularity. To this end, in this paper, we propose a novel Adaptive Hierarchical Graph Cut network (AHGC) to deeply explore the semantic relationship between different images. Specifically, we construct a hierarchical KNN graph to evaluate the similarities between different images based on the cosine similarity. Based on the linkage and density information of the graph, we cut the graph into multiple subgraphs to integrate these semantics-similar samples. If the labeled percentage in a subgraph is larger than a threshold, we will assign the label with the highest percentage to unlabeled images. To further improve the model generalization, we augment each image into two augmentation versions, and maximize the similarity between the two versions. Finally, we leverage the similarity score for OOD detection. Extensive experiments on two challenging benchmarks (CIFAR-10 and CIFAR-100) illustrate that in representative cases, AHGC outperforms state-of-the-art OOD detection methods by 81.24% on CIFAR-100 and by 40.47% on CIFAR-10 in terms of 'FPR95'. © 2020 IEEE.

关键词： Graphitization

来源：评论

学校读者我要写书评

暂无评论

Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation

引用

IFAC-PapersOnLine 2023年第2期56卷 9056-9061页

作者： Vittorio Giammarino James Queeney Lucas C. Carstensen Michael E. Hasselmo Ioannis Ch Paschalidis Division of Systems Engineering Boston University Boston MA 02215 USA Center for Systems Neuroscience Department of Psychological and Brain Sciences and Graduate Program for Neuroscience Boston University Boston MA 02215 USA College of Engineering and Hariri Institute for Computing & Computational Science & Engineering Boston University Boston MA 02215 USA

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a 2D navigation task. We show how the use of animal videos improves performance over RL algorithms that do not leverage such observations.

关键词： Learning for Control Reinforcement Learning Deep Learning RL with demonstrations Imitation Learning Bio-inspired Control

来源：评论

学校读者我要写书评

暂无评论

Large Scale Finite-Temperature Real-time Time Dependent Density Functional Theory Calculation with Hybrid Functional on ARM and GPU Systems

arXiv

引用

arXiv 2025年

作者： Liu, Rongrong Guo, Zhuoqiang Sha, Qiuchen Zhao, Tong Li, Haibo Hu, Wei Liu, Lijun Tan, Guangming Jia, Weile State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China School of Mathematics and Statistics The University of Melbourne Melbourne Australia School of Computer Science and Technology University of Science and Technology of China Hefei China Department of Mechanical Engineering Graduate School of Engineering Osaka University Osaka Japan

Ultra-fast electronic phenomena originating from finite temperature, such as nonlinear optical excitation, can be simulated with high fidelity via real-time time dependent density functional theory (rt-TDDFT) calculations with hybrid functional. However, previous rt-TDDFT simulations of real materials using the optimal gauge-known as the parallel transport gauge-have been limited to low-temperature systems with band gaps. In this paper, we introduce the parallel transport-implicit midpoint (PT-IM) method, which significantly accelerates finite-temperature rt-TDDFT calculations of real materials with hybrid function. We first implement PT-IM with hybrid functional in our plane wave code PWDFT, and optimized it on both GPU and ARM platforms to build a solid baseline code. Next, we propose a diagonalization method to reduce computation and communication complexity, and then, we employ adaptively compressed exchange (ACE) method to reduce the frequency of the most expensive Fock exchange operator. Finally, we adopt the ring_based method and the shared memory mechanism to overlap computation and communication and alleviate memory consumption respectively. Numerical results show that our optimized code can reach 3072 atoms for rt-TDDFT simulation with hybrid functional at finite temperature on 192 computing nodes, the time-to-solution for one time step is 429.3s, which is 41.4 times faster compared to the baseline. © 2025, CC BY-NC-SA.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Integrated Beamforming and Resource Allocation in RIS-Assisted mmWave Networks based on Deep Reinforcement Learning

Integrated Beamforming and Resource Allocation in RIS-Assist...

引用

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Di Chen Hui Gao Na Chen Ruohan Cao Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Japan

Reconfigurable intelligent surface (RIS) has gained wide attention recently as a promising solution to address the blockage issue in millimeter wave (mmWave) communication networks. In this paper, we consider a RIS-assisted mmWave communication system consisting of multiple RISs and users. A novel integrated scheme based on deep reinforcement learning (DRL) is proposed to jointly optimize the hybrid beamforming, phase shifts, and power allocation. Specifically, we design a multi-variable action output to achieve integrated optimization in both beam and power domains. We also design a weighted sum reward to balance the influence of beam and power domain optimizing variables in the training process. Experimental results demonstrate that the proposed DRL-based method can achieve at least 37% higher sum rates than the baseline algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Higher-Order Bloch Sphere: Geometric Representation of Larmor Precession of the Higher-Order Spin States

Higher-Order Bloch Sphere: Geometric Representation of Larmo...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Sota Sato Toshiki Matsumoto Satoshi Iba Katsuhiko Miyamoto Takashige Omatsu Ken Morita Graduate School of Science and Engineering Chiba University Department of Electrical and Electronic Engineering Chiba University Research Center for Emerging Computing Technologies National Institute of Advanced Industrial Science and Technology

We propose an analogous sphere, herein referred a higher-order Bloch sphere (HOBS), to visualize the Larmor precession of higher-order spin. Our proposed HOBS is potentially applied to advanced quantum information pro...

关键词：

来源：评论

学校读者我要写书评

暂无评论

MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint

arXiv

引用

arXiv 2024年

作者： Zhou, Xinglin Yuan, Yifu Yang, Shaofu Hao, Jianye School of Computer Science and Engineering Southeast University Nanjing210096 China Southeast University-Monash University Joint Graduate School Southeast University Suzhou215123 China College of Intelligence and Computing Tianjin University Tianjin300072 China

Hierarchical reinforcement learning (HRL) provides a promising solution for complex tasks with sparse rewards of agents, which uses a hierarchical framework that divides tasks into subgoals and completes them sequentially. However, current methods struggle to find suitable subgoals for ensuring a stable learning process. To address the issue, we propose a general hierarchical reinforcement learning framework incorporating human feedback and dynamic distance constraints, termed MENTOR, which acts as a "mentor". Specifically, human feedback is incorporated into high-level policy learning to find better subgoals. Furthermore, we propose the Dynamic Distance Constraint (DDC) mechanism dynamically adjusting the space of optional subgoals, such that MENTOR can generate subgoals matching the low-level policy learning process from easy to hard. As a result, the learning efficiency can be improved. As for lowlevel policy, a dual policy is designed for exploration-exploitation decoupling to stabilize the training process. Extensive experiments demonstrate that MENTOR uses a small amount of human feedback to achieve significant improvement in complex tasks with sparse rewards. Further details and code implementations can be found at https://***/nidesuipao/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

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：