检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zeng, Hongchuan Xu, Hongshen Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9782493814104

Large Language Models (LLMs) have ushered in a new era in Natural Language Processing, but their massive size demands effective compression techniques for practicality. Although numerous model compression techniques have been investigated, they typically rely on a calibration set that overlooks the multilingual context and results in significant accuracy degradation for low-resource languages. This paper introduces Multilingual Brain Surgeon (MBS), a novel calibration data sampling method for multilingual LLMs compression. MBS overcomes the English-centric limitations of existing methods by sampling calibration data from various languages proportionally to the language distribution of the model training datasets. Our experiments, conducted on the BLOOM multilingual LLM, demonstrate that MBS improves the performance of existing English-centric compression methods, especially for low-resource languages. We also uncover the dynamics of language interaction during compression, revealing that the larger the proportion of a language in the training set and the more similar the language is to the calibration language, the better performance the language retains after compression. In conclusion, MBS presents an innovative approach to compressing multilingual LLMs, addressing the performance disparities and improving the language inclusivity of existing compression techniques. The codes are available at: https://***/X-LANCE/MBS. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Recognition with Convolutional Neural Networks using DL 2

Facial Emotion Recognition with Convolutional Neural Network...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Rao, M. Srinivasa Kiran, Ajmeera Naik, S.K. Lokesh Kumar, A. Pramod Swamy, K. Kotaiah Devika, P. Mlr Institute of Technology Department of Electronics and Communication Engineering Hyderabad India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India and Ai&ds Hyderabad India Aiml Vnr Vignana Jyothi Institute of Enginnering and Technology Department of Cse Hyderabad India

ISBN: (纸本)9798350370188

In this universe, facial expressions reveal a person's mood. One thing is certain: every expression expresses feelings. Artificial intelligence (ai) lets us distinguish a variety of emotions, even though everyone has a unique set of facial features and emotional repertoire. Face emotion-recognition ais can be built using deep learning. Create a convolutional neural network (CNN) to train the dataset and get high prediction accuracy using this method. The goal is to identify seven basic face expressions among hundreds. Happy, sad, neutral, anger, surprise, fear, and contempt are the most common facial expressions, followed by neutrality. This facial expression identification can be done using deep face algorithms, machine learning, other ai methods, TensorFlow, etc. Our model is 70%-80% accurate. This method may be the easiest and most effective. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

DCBLCCG NET: A Fusion Approach For Enhanced Pepper Leaf Disease Identification With Hybrid Deep Learning

DCBLCCG NET: A Fusion Approach For Enhanced Pepper Leaf Dise...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Shaik Salma Asiya Begum Hussainbi Shaik Hussain Syed Department of CSE(AI&ML) LakiReddy Bali Reddy College of Engineering Mylavaram NTR District AP India School of Computer Science and Engineering VIT-AP University Amaravati AP India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

The agricultural sector in developing countries like Ethiopia heavily relies on crop health and productivity. Pepper, a crucial crop for global food security, faces significant threats from various diseases, including blight leaf disease, gray leaf spot, common rust, fruit rot, and powdery mildew. The existence of 34 different pepper diseases has resulted in an average reduction of 33% in crop productivity. Traditional disease detection methods, such as visual inspection by farmers, are prone to errors and are time-consuming Previous research has largely employed image processing and deep learning for disease classification in pepper plants. This study introduces a novel approach by combining a Deep Convolutional Neural Network (DCNN) with a Bidirectional Long Short-Term Memory (BILSTM) network. While DCNN excels at extracting spatial features, BILSTM captures the sequential growth patterns of pepper plants. This hybrid model achieved $\mathbf{1 0 0 \%}$ accuracy during training and performed exceptionally well on a dataset of pepper disease images. Utilizing features from pretrained CNNs like VGG16 and AlexNet, the model attained a top classification accuracy of $\mathbf{9 9. 5 \%}$, with grayscale datasets and segmented images achieving $\mathbf{9 8. 9 \%}$ and $\mathbf{9 9. 3} \%$, respectively. This robust model is a powerful tool for rapid and accurate pepper disease identification, improving disease management and agricultural productivity.

关键词： Productivity Image segmentation Accuracy Microorganisms Transfer learning Bidirectional long short term memory Crops Gray-scale Feature extraction Diseases

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis and Framework for Text and Graphics Separation in Document Images

Comprehensive Analysis and Framework for Text and Graphics S...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Shweta Singh Sudeep Varshney Ankur Chaudhary Department of CSE Sharda School of Engineering & Technology Sharda University Greater Noida AI/ML Computational Science Manager Accenture Pvt Ltd

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

The process of breaking up a digital image into many parts is called segmentation. These sections in scanned papers, are those that have backgrounds, texts, and images. In applications linked to document analysis, text segmentation is a significant issue. The separation of a complex document into non-text and text components is a major challenge in document image analysis. Localization of text in printed document images is a critical processing step for page layout analysis (PLA), specifically for obtaining textual data. Several algorithms have been developed for this subject. However, many algorithms only produce accurate answers for a limited type of documents due to their reliance on specific attributes or assumptions. There is a need to develop effective techniques for many sorts of documents, such as newspapers, magazines, documents, and articles, with arbitrary layouts and nonhomogeneous backgrounds. This study examines the various ways that distinguish between non-text and text in document images.

关键词： Surveys Location awareness Image segmentation Text analysis Image analysis Reviews Digital images Layout Optical character recognition Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Solution to finding Fruit Freshness Index using computer Vision

A Solution to finding Fruit Freshness Index using Computer V...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： S Ashwin Raja T.R. Vijay Srivatsan G. Maragatham Computer Science with AI & ML SRMIST KTR Chennai India Department of Computational Intelligence SRM Institute Of Science And Technology KTR

Fruits have now become a product to the market's eye, as fruits being the top recommended food to be consumed for better health, the prices drive higher and higher day by day. The main reason for the increase in the price of fruits is the manual labor behind it. It is the sorting and grading done by such humans which takes a prolonged period of time, inconsistent, onerous, subjective, variable, costly and influenced by other factors such as the environment around them which holds these fruits at an untouchable rate to the normal low paid consumers. To tackle this and hopefully reduce the rising price in fruits we have come up with a solution that a Fruit freshness System needs to be put in place. As computer vision has been used by many researchers to sort and grade fruits, we decided the best way to aid our solution would be by the implementation of computer Vision. The summary of this paper is that it provides an overview of the many methods which have been implemented to reduce and lower the manual labor in the grading and sorting of fruits in the market i.e., feature extraction, segmentation, preprocessing, classification which addresses the fruits and the quality of the fruits based on texture, color, shape, size, and it's defects. These steps lead to a much more accurate shelf-life date of the fruits which also tackles the problem of food wastage, this will decrease the wastage of fruits from turning spoiled much earlier than expected.

关键词： computer vision Shape Image color analysis Manuals Image capture Feature extraction Turning

来源：评论

学校读者我要写书评

暂无评论

Locate N’ Rotate: Two-Stage Openable Part Detection with Foundation Model Priors 17th

Locate N’ Rotate: Two-Stage Openable Part Detection with F...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Li, Siqi Chen, Xiaoxue Cheng, Haoyu Zhou, Guyue Zhao, Hao Tian, Guanzhong Ningbo innovation Center Zhejiang University Hangzhou China College of Control Science and Engineering Zhejiang University Hangzhou China Institute for AI Industry Research Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9789819609628

Detecting the openable parts of articulated objects is crucial for downstream applications in intelligent robotics, such as pulling a drawer. This task poses a multitasking challenge due to the necessity of understanding object categories and motion. Most existing methods are either category-specific or trained on specific datasets, lacking generalization to unseen environments and objects. In this paper, we propose a Transformer-based Openable Part Detection (OPD) framework named Multi-feature Openable Part Detection (MOPD) that incorporates perceptual grouping and geometric priors, outperforming previous methods in performance. In the first stage of the framework, we introduce a perceptual grouping feature model that provides perceptual grouping feature priors for openable part detection, enhancing detection results through a cross-attention mechanism. In the second stage, a geometric understanding feature model offers geometric feature priors for predicting motion parameters. Compared to existing methods, our proposed approach shows better performance in both detection and motion parameter prediction. Codes and models are publicly available at https://***/lisiqi-zju/MOPD. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE STOCHASTIC GRADIENT ALGORITHM FOR BLACK-BOX MULTI-OBJECTIVE LEARNING 12

ADAPTIVE STOCHASTIC GRADIENT ALGORITHM FOR BLACK-BOX MULTI-O...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ye, Feiyang Lyu, Yueming Wang, Xuehao Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Shanghai Artificial Intelligence Laboratory China School of Computer Science and Engineering Nanyang Technological University Singapore

Multi-objective optimization (MOO) has become an influential framework for various machine learning problems, including reinforcement learning and multitask learning. In this paper, we study the black-box multi-objective optimization problem, where we aim to optimize multiple potentially conflicting objectives with function queries only. To address this challenging problem and find a Pareto optimal solution or the Pareto stationary solution, we propose a novel adaptive stochastic gradient algorithm for black-box MOO, called ASMG. Specifically, we use the stochastic gradient approximation method to obtain the gradient for the distribution parameters of the Gaussian smoothed MOO with function queries only. Subsequently, an adaptive weight is employed to aggregate all stochastic gradients to optimize all objective functions effectively. Theoretically, we explicitly provide the connection between the original MOO problem and the corresponding Gaussian smoothed MOO problem and prove the convergence rate for the proposed ASMG algorithm in both convex and non-convex scenarios. Empirically, the proposed ASMG method achieves competitive performance on multiple numerical benchmark problems. Additionally, the state-of-the-art performance on the black-box multi-task learning problem demonstrates the effectiveness of the proposed ASMG method. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-Robot Interaction through Natural Language Processing and Speech Recognition Techniques

Enhancing Human-Robot Interaction through Natural Language P...

引用

International Conference on Computational and Characterization Techniques in engineering & sciences (CCTES)

作者： Thotakura Veeranna K. Pavan Kumar Mahadeva Aruna Amit Verma Thanu Kurian Department of CSE(AI&ML) Sai Spurthi Institute of Technology B. Gangaram India Department of Electronics & Communication Engineering (ECE) K.S.R.M College of Engineering(Autonomous) Kadapa India Computer Science and Engineering Sai Spurthi Institute of Technology B. Gangaram India Department of Computer Science and Engineering Dr. K N Modi University Newai Rajasthan India Department of AI &ML New Horizon College of Engineering Bangalore India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

The rapid development of artificial intelligence (ai) has resulted in the gradual integration of robots into individuals' everyday lives and professional environments. The use of image recognition employing the robot's human-machine interface technology has become widespread. However, there are still some unresolved problems with the methods used for interaction between robots and machines, such as natural language processing (NLP) and speech recognition. Thus, building on previous research in the field, this work suggests a novel approach to robot-machine interaction by integrating the perceptron lexicon analysis model with the transfer dependence syntactic analysis model. To enhance interaction performance, researchers need to delve further into language-based human-machine interaction systems. An experimental evaluation of the structural perceptron model reveals a recall rate of 82%, an F1 value of 83%, and a testing accuracy of 96%. A maximum analysis of data speed of 751K/s is achieved using the data transfer dependence syntax analysis model. With superior robustness and reaction sensitivity, the novel technique for robot-machine interaction achieves a 93% accuracy rate in comparison to previous methods that have been tested in simulations. To conclude, research methodologies provide the foundation, both theoretically and practically, for better human-machine cooperation and enhanced robot interaction skills)

关键词： Human computer interaction Analytical models Adaptation models Accuracy Human-machine systems Speech recognition Syntactics Robot sensing systems Natural language processing Testing

来源：评论

学校读者我要写书评

暂无评论

RDT-1B: A DIFFUSION FOUNDATION MODEL FOR BIMANUAL MANIPULATION

arXiv

引用

arXiv 2024年

作者： Liu, Songming Wu, Lingxuan Li, Bangguo Tan, Hengkai Chen, Huayu Wang, Zhengyi Xu, Ke Su, Hang Zhu, Jun Department of Computer Science & Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China

Bimanual manipulation is essential in robotics, yet developing foundation models is extremely challenging due to the inherent complexity of coordinating two robot arms (leading to multi-modal action distributions) and the scarcity of training data. In this paper, we present the Robotics Diffusion Transformer (RDT), a pioneering diffusion foundation model for bimanual manipulation. RDT builds on diffusion models to effectively represent multi-modality, with innovative designs of a scalable Transformer to deal with the heterogeneity of multi-modal inputs and to capture the nonlinearity and high frequency of robotic data. To address data scarcity, we further introduce a Physically Interpretable Unified Action Space, which can unify the action representations of various robots while preserving the physical meanings of original actions, facilitating learning transferrable physical knowledge. With these designs, we managed to pre-train RDT on the largest collection of multi-robot datasets to date and scaled it up to 1.2B parameters, which is the largest diffusion-based foundation model for robotic manipulation. We finally fine-tuned RDT on a self-created multi-task bimanual dataset with over 6K+ episodes to refine its manipulation capabilities. Experiments on real robots demonstrate that RDT significantly outperforms existing methods. It exhibits zero-shot generalization to unseen objects and scenes, understands and follows language instructions, learns new skills with just 1∼5 demonstrations, and effectively handles complex, dexterous tasks. We refer to the project page for the code and videos. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Assessment of Elite Football Players Based on Anthropometric and Motor Fitness Parameters with Regard to their Playing Positions

引用

SN computer science 2024年第8期5卷 1-10页

作者： Sneha, Santoshi Prithvi, B.S. Niranjanamurthy, M. Kiran Kumar, H.K. Dayananda, P. MediNXT Technologies Pvt Ltd Bangalore India Department of Computer Science and Engineering Aditya College of Engineering and Technology (affiliated to Visvesvaraya Technological University Belagavi) Bangalore 560089 India Department of AI and ML BMS Institute of Technology and Management (affiliated to Visvesvaraya Technological University Belagavi) Bangalore India Department of Physical Education M S Ramaiah Institute of Technology (affiliated to Visvesvaraya Technological University Belagavi) Bangalore India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Sports players strive to be the epitome of human excellence, pushing the barrier of skill and execution with training, focus and direction, amplified by regular training and practice. This could be attributed to various factors such as response to stimuli, physical factors, psychological factors etc. The present study incorporated the prediction of the most suited playing position of elite male football players using machine learning approaches based on their Anthropometric Parameters (AP–11 parameters) and Motor Fitness Parameters (MFP–7 parameters). Of the features analysed, results identified the position indicative nature of some parameters among6 AP (Height, Body Mass Index, Basal Metabolic Rate, Fat %, Thigh Circumference, Calf circumference) and 4 MFP (120 m, 80 m, 40 m dash and T-Test) by Spearman’s Rank Correlation Test. Further, the prediction of ideal playing position was achieved using various classifiers such as Support Vector Machine (SVM), SVM with over sampled data, SVM with hyperparameter tuning, SVM with variable scaling and Extreme Gradient Boosting (XG Boost). Among these, the highest classification accuracy and f1-score at 92% and 0.92 respectively were obtained for XG Boost Classifier which portrayed a faster performance as compared to the other approaches. The present study could be useful in professional sports training and rehabilitation so as to help the players perform better in the football game. © The Author(s) 2024.

关键词： Anthropometric parameters Football players Hyperparameter tuning Physiological parameters Spearman’s rank correlation test XG boost classifier

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：