检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 1545-1576页

作者： Dahuin Jung Hyungyu Lee Sungroh Yoon Electrical and Computer Engineering Seoul National University Seoul Republic of Korea Electrical and Computer Engineering Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Republic of Korea

Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined. However, imitation learning methods still require numerous expert demonstration samples to successfully imitate an expert's behavior. To improve sample efficiency, we utilize self-supervised representation learning, which can generate vast training signals from the given data. In this study, we propose a self-supervised representation-based adversarial imitation learning method to learn state and action representations that are robust to diverse distortions and temporally predictive, on non-image control tasks. In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions. We theoretically and empirically observe that making an informative feature manifold with less sample complexity significantly improves the performance of imitation learning. The proposed method shows a 39% relative improvement over existing adversarial imitation learning methods on MuJoCo in a setting limited to 100 expert state-action pairs. Moreover, we conduct comprehensive ablations and additional experiments using demonstrations with varying optimality to provide insights into a range of factors.

关键词： imitation learning adversarial imitation learning self-supervised learning data efficiency

来源：评论

学校读者我要写书评

暂无评论

Statistical Device Simulation and Machine Learning of Process Variation Effects of Vertically Stacked Gate-All-Around Si Nanosheet CFETs

引用

IEEE Transactions on Nanotechnology 2024年 23卷 386-392页

作者： Kola, Sekhar Reddy Li, Yiming Butola, Rajat National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Biomedical Engineering Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation Hsinchu300093 Taiwan

In this study, we report the process variation effect (PVE) including the work function fluctuation (WKF) on the DC/AC characteristic fluctuation of stacked gate-all-around silicon complementary field-effect transistors (CFETs). The PVE affects characteristic fluctuation significantly;in particular, for the variability of off-state current. Owing to the bottom channel of a fin-type, the P-FET suffers from the worst off-state current fluctuation (more than 200% variation) compared to the N-FET. The device variability induced by the WKF is marginal because of amorphous-type metal grains. As input features to an artificial neural network (ANN) model, low and high work function values, as well as parameters of PVE that have prevalent effects on CEFT transfer characteristics are further considered and modeled. The estimated values of R2-score prove that the ANN model properly grasps information from the dataset successfully;thus, it can be used to model emerging CFETs for circuit simulation. © 2002-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Camera-Only Perception System for Traffic Jam Assistance

Camera-Only Perception System for Traffic Jam Assistance

引用

2023 International Automatic Control Conference, CACS 2023

作者： Huang, Xiao-Wei Chen, Xiu-Zhi Chen, Yen-Lin National Taipei University of Technology Master Program in Artificial Intelligence Technology Taipei Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350306354

Traditional perception systems for TJA (Traffic Jam Assistance) are mostly implemented by fusing images with radar or lidar. As computer vision techniques become more powerful, cameras can almost replace the need for radar and lidar in perception tasks, which reduces the hardware cost of the system. In this research, we propose a camera-only perception system for TJA, which is able to provide the information of the vehicles ahead and the drivable area. The proposed system has been evaluated through real-world scenario sequences, and proved that it achieves high robustness, which is highly possible to be adopted for TJA development. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting 38

Introducing Spectral Attention for Long-Range Dependency in ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kang, Bong Gyun Lee, Dongjun Kim, HyunGi Chung, DoHyun Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Future Automotive Mobility Seoul National University Korea Republic of

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture long-range dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results. © 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

Robust Object Detection Model for UAV Application

Robust Object Detection Model for UAV Application

引用

2023 International Automatic Control Conference, CACS 2023

作者： Ku, Chun Chen, Xiu-Zhi Chen, Yen-Lin National Taipei University of Technology Master Program in Artificial Intelligence Technology Taipei Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350306354

Not only common issues on object detection task need to be deal with, for Unmanned Aerial Vehicle (UAV) applications, small object is one of the critical problems that needs to be solved. YOLOv7 is a powerful network architecture that provides high efficiency and accuracy object detection results. This paper adopts YOLOv7 as an object detection model for two different kinds of targets, one is vehicle, and the other is ocean flotsam. By training the model with open datasets and fine-tuning the model with self-collected datasets, we prove through sequences collected from real-world scenarios that YOLOv7 is able to provide robust and accurate object detection results, including vehicles and ocean flotsam, with real-time efficiency. Based on such experimental result, we confirmed that YOLOv7 can be the baseline for object detection model development. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Text2PointCloud: Text-Driven Stylization for Sparse PointCloud

Text2PointCloud: Text-Driven Stylization for Sparse PointClo...

引用

44th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2023

作者： Hwang, Inwoo Kim, Hyeonwoo Lim, Donggeun Park, Inbum Kim, Young Min Seoul National University Department of Electrical and Computer Engineering Korea Republic of Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Korea Republic of

ISBN: (纸本)9783038682097

We present Text2PointCloud, a method to process sparse, noisy point cloud input and generate high-quality stylized output. Given point cloud data, our iterative pipeline stylizes and deforms points guided by a text description and gradually densifies the point cloud. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated 3D datasets with high-quality textures, which are produced by skillful artists or high-resolution colored 3D models. Also, since we represent 3D shapes as a point cloud, we can visualize fine-grained geometric variations with a complex topology such as flowers or fire. To the best of our knowledge, it is the first approach for directly stylizing the uncolored, sparse point cloud input without converting it into a mesh or implicit representation, which might fail to express the original information in the measurements, especially when the object exhibits complex topology. © 2023 Authors.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Mental Status Identification for Infertile Patients Using artificial intelligence Models 14th

Mental Status Identification for Infertile Patients Using Ar...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Hsu, Hao-Siang Wang, Jong-Yi Chiou, Hai-Chi Wu, Fu-Hsing Lin, Chuen-Horng Chan, Yung‑Kuan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404336 Taiwan Department of Health Services Administration China Medical University Taichung406040 Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung404336 Taiwan Department of Management Information Systems National Chung-Hsing University Taichung402202 Taiwan

ISBN: (纸本)9789819623945

Infertile patients may be a high-risk group of mental disorder. The precise identification of the mental status of infertile patients can provide decision support to healthcare professionals and may be helpful in providing preventive measures accordingly. Rare studies focused on the mental status identification using artificial intelligence (AI) models for infertile people. This study aimed to precisely identify the mental status (anxiety and depression) of infertile patients using three AI models, the XGBoost, decision tree, and stacking models. The dataset, retrieved from a structured questionnaire survey in 2011, which included 400 infertility outpatients seeking reproductive treatments at three teaching hospitals in Taiwan was adopted for training and testing AI models. Aforementioned AI models were designed and reached identification performances of accuracy, precision, recall and area under ROC curve (AUC) equaling 0.75–0.82, 0.70–0.80, 0.64–0.72, and 0.64–0.72, respectively. The XGBoost model (accuracy = 0.82, precision = 0.80, recall = 0.72, and AUC = 0.72) outperformed or equaled the decision tree and stacking models in terms of accuracy, precision, recall, and AUC values. Designed AI models for mental status identification can be integrated into the clinical decision support system (CDSS) to provide the anxiety and depression group automatically. Accordingly, the worsening of infertility-related anxiety and depression can be prevented. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： artificial intelligence infertile patients Mental status identification stacking model XGBoost

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Deep Learning Technologies

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Dee...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： El-Sheikh, Mohamed M. Bayoumy, Aya Ahmed, Nada M. Mohamed Eldeeb, Amany Rabea, Fatma I. Nawar, Amira A. Khattap, Mohamed G. Galal Eldeen Mohamed Ali Hassan, Hend Mostafa, Mariam Ibrahim, Nayra Ramadan, Reem Refaat, Yomna Khaled, Mennatallah Maher, Ali Abd Elaziz, Mohamed Gamal Abdellatif Ibrahim, Ahmed Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez435611 Egypt Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Air Defense College Department of Electronics and Electrical Communications Engineering Alexandria Egypt

ISBN: (纸本)9798350351408

This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Real-time multilingual speech recognition and speaker diarization system based on Whisper segmentation

引用

PeerJ computer Science 2024年 10卷 e1973页

作者： Lyu, Ke-Ming Lyu, Ren-yuan Chang, Hsien-Tsung Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Physical Medicine and Rehabilitation Chang Gung Memorial Hospital Taoyuan Taiwan Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan Taiwan

This research presents the development of a cutting-edge real-time multilingual speech recognition and speaker diarization system that leverages OpenAI’s Whisper model. The system specifically addresses the challenges of automatic speech recognition (ASR) and speaker diarization (SD) in dynamic, multispeaker environments, with a focus on accurately processing Mandarin speech with Taiwanese accents and managing frequent speaker switches. Traditional speech recognition systems often fall short in such complex multilingual and multispeaker contexts, particularly in SD. This study, therefore, integrates advanced speech recognition with speaker diarization techniques optimized for real-time applications. These optimizations include handling model outputs efficiently and incorporating speaker embedding technology. The system was evaluated using data from Taiwanese talk shows and political commentary programs, featuring 46 diverse speakers. The results showed a promising word diarization error rate (WDER) of 2.68% in twospeaker scenarios and 11.65% in three-speaker scenarios, with an overall WDER of 6.96%. This performance is comparable to that of non-real-time baseline models, highlighting the system’s ability to adapt to various complex conversational dynamics, a significant advancement in the field of real-time multilingual speech processing. © 2024 Lyu et al.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Adversarial environment design via regret-guided diffusion models 24

Adversarial environment design via regret-guided diffusion m...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hojun Chung Junseo Lee Minsoo Kim Dohyeong Kim Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Department of Electrical and Computer Engineering and ASRI Seoul National University Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University and Department of Electrical and Computer Engineering and ASRI Seoul National University

ISBN: (纸本)9798331314385

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD

关键词：

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：