检索结果-内蒙古大学图书馆

Evaluation of OpenAI o1: Opportunities and Challenges of AGI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhong, Tianyang Liu, Zhengliang Pan, Yi Zhang, Yutong Zhou, Yifan Liang, Shizhe Wu, Zihao Lyu, Yanjun Shu, Peng Yu, Xiaowei Cao, Chao Jiang, Hanqi Chen, Hanxu Li, Yiwei Chen, Junhao Hu, Huawen Liu, Yihen Zhao, Huaqin Xu, Shaochen Dai, Haixing Zhao, Lin Zhang, Ruidong Zhao, Wei Yang, Zhenyuan Chen, Jingyuan Wang, Peilong Ruan, Wei Wang, Hui Zhao, Huan Zhang, Jing Ren, Yiming Qin, Shihuan Chen, Tong Li, Jiaxi Zidan, Arif Hassan Jahin, Afrar Chen, Minheng Xia, Sichen Holmes, Jason Zhuang, Yan Wang, Jiaqi Xu, Bochen Xia, Weiran Yu, Jichao Tang, Kaibo Yang, Yaxuan Sun, Bolun Yang, Tao Lu, Guoyu Wang, Xianqiao Chai, Lilong Li, He Lu, Jin Sun, Lichao Zhang, Xin Ge, Bao Hu, Xintao Zhang, Lian Zhou, Hua Zhang, Lu Zhang, Shu Liu, Ninghao Jiang, Bei Kong, Linglong Xiang, Zhen Ren, Yudan Liu, Jun Jiang, Xi Bao, Yu Zhang, Wei Li, Xiang Li, Gang Liu, Wei Shen, Dinggang Sikora, Andrea Zhai, Xiaoming Zhu, Dajiang Zhang, Tuo Liu, Tianming Department of Mathematical and Statistical Sciences University of Alberta Edmonton Canada School of Computing University of Georgia GA United States Institute of Medical Research Northwestern Polytechnical University Xi'An China College of Arts and Sciences University of Georgia Athens United States Institute of Plant Breeding Genetics & Genomics University of Georgia AthensGA United States Department of Computer Science and Engineering University of Texas ArlingtonTX United States The Lamar Dodd School of Art University of Georgia GA United States School of Computer Science Northwestern Polytechnical University Xi'An China School of Automation Northwestern Polytechnical University Xi'An China University of California Los AngelesCA United States Department of Radiology The Second Xiangya Hospital Central South University Changsha China Clinical Research Center for Medical Imaging in Hunan Province Changsha China Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Guanghua School of Management Peking University Beijing China Department of Radiation Oncology Mayo Clinic PhoenixAZ United States Second Language Acquisition and Teaching University of Arizona TucsonAZ United States School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China The First Hospital of Hebei Medical University Hebei Shijiazhuang China School of Computer and Cyber Sciences Augusta University AugustaGA United States School of Physics and Information Technology Shaanxi Normal University Xi'An China School of Future Technology South China University of Technology Guangzhou China Department of Radiology and BRIC University of North Carolina Chapel HillNC United States Department of Educational Psychology University of Georgia AthensGA United States Johns Hopkins University BaltimoreMD United States School of Architecture Tsinghua Universit

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: • 83.3% success rate in solving complex competitive programming problems, surpassing many human experts. • Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. • 100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. • Advanced natural language inference capabilities across general and specialized domains like medicine. • Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. • Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. • Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. • Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence. This evaluation not only highlights o1-preview's current strengths and limitations but also identifies crucial areas for future development, including multi-modal integratio

关键词： Emotion Recognition

Identifying Hierarchical Individual Functional Network under Naturalistic Paradigm via Two-stage DBN with Neural architecture Search 4

学校读者我要写书评

暂无评论

Identifying Hierarchical Individual Functional Network under...

4th International Symposium on Image Computing and Digital Medicine, ISICDM 2020

作者： Tao, Zeyang Ren, Yudan Zhang, Wei Liu, Tianming School of Information Science AND Technology Northwest University Xi'an China Department of Radiology and Biomedical Imaging University of California San FranciscoCA United States Cortical Architecture Imaging and Discovery Lab Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States

ISBN: (纸本)9781450389686

Functional magnetic resonance imaging under naturalistic paradigm (NfMRI) is gaining increasing attraction, as it offers an ecologically-valid condition to understand brain function in real life. Characterizing the hierarchical organization of brain function while taking the nature of fMRI activities under naturalistic condition into account has been a critical issue in identifying naturalistic functional networks. Recent studies have made efforts on characterizing the brain's hierarchical organizations from fMRI data via a variety of deep learning models. However, most of those models have ignored the properties of group-wise consistency and inter-subject difference in brain function under naturalistic paradigm. Another critical issue is how to determine the optimal neural architecture of deep learning models, as manual design of neural architecture is time-consuming and less reliable. To tackle these problems, we proposed a two-stage deep belief network (DBN) with neural architecture search (NAS) combined framework (two-stage NAS-DBN framework) to model both the group-consistent and individual-specific naturalistic functional brain networks. Our results demonstrated that the optimized DBN-based framework can characterize meaningful group-wise and individual-level naturalistic functional networks, which reflected the hierarchical organization of brain function and the properties of brain functional activities under naturalistic paradigm. © 2020 ACM.

关键词： Brain

Emotional evaluation of architectural interior forms based on personality differences using virtual reality

学校读者我要写书评

暂无评论

Frontiers of Architectural Research 2020年第1期9卷 138-147页

作者： Maryam Banaei Ali Ahmadi Klaus Gramann Javad Hatami School of Architecture and Environmental Design Iran University of Science and TechnologyTehranIran Faculty of Computer Engineering K.N.Toosi UniversityTehranIran Department of Psychology and Ergonomics Biological Psychology and NeuroergonomicsBerlin Institute of TechnologyBerlinGermany Center for Advanced Neurological Engineering University of CaliforniaSan DiegoCAUSA School of Software University of Technology SydneySydneyAustralia Department of Psychology University of TehranTehranIran

Recent studies have shown that architectural interior forms could impact the affective state of ***,the direct relation of specific forms with specific affective states is difficult to *** addition,no systematic categorization of architectural forms and their relation to emotional states *** investigation of the impact of architectural features on inhabitants'emotions is further complicated by the use of two-dimensional images of forms in laboratory investigations,which cannot perceive real-world ***,the interior form consists of a combination of different forms rather than only pure forms,which was considered in previous *** study aimed to rill these gaps by evaluating interior forms on the basis of clustering different images of built living rooms throughout history as well as their impact on *** study used pleasure,arousal,and dominance ratings with an emphasis on individual differences in *** sample rooms were created based on formal clusters of architectural *** showed a relationship between forms and emotional states for different personality *** work provided a novel approach on the influence of architecture on emotion by considering systematic form categorization and combinations,personality differences,and a virtual reality setup.

关键词： Architectural interior form PAD Self-assessment manikin Personality Virtual reality

Cap-Eye-citor: A Machine Vision Inference Approach of Capacitor Detection for PCB Automatic Optical Inspection 7

学校读者我要写书评

暂无评论

Cap-Eye-citor: A Machine Vision Inference Approach of Capaci...

7th IEEE International Conference on Engineering Technologies and Applied sciences, ICETAS 2020

作者： Susa, Julie Ann B. Mariquina, Erwin Tria, Meriam L. Adolfo, Cid Mathew Castro, Julius C. Technological Institute of the Philippines College of Engineering and Architecture Manila Philippines International Electronics and Technical Institute Department of Computer Engineering Alabang Philippines Eulogio"Amang"Rodriguez Institute of Science and Technology Department of Electronics Engineering Manila Philippines University of Gloucestershire School of Computing and Engineering United Kingdom Bohol Island State University Department of Computer Engineering Bohol Philippines

ISBN: (纸本)9780738105048

Circuit boards are one of the key elements of the electronics industry. Because of its demand for portable electronic goods, the production of circuit boards has become more significant. The most significant aspect of printed circuit board production is AOI or Automatic Optical Inspection. When generated in a single quantity, the PCB requires a small way to teach and change the AOI method for process validation. This paper proposes a mechanism of detection of capacitors trained on circuit boards using the YOLO V3 algorithm. YOLO is a form of rapid object detection based on the convolutional neural network or CNN. CNN's deep network can distinguish specific characteristics from all the image features. The study developed an AI with the same feature that the manufacturing industry uses to assist students with an effective evaluation of their circuit boards. It focuses on the capacitor in a circuit board. It will not, however, be capable of distinguishing other forms of electronic components. Nearly 60 percent of the entire test has a performance of 100 percent detection, according to the test results, while 33.33 percent is over 70 percent detection and 6.66 percent has a 0 percent detection output. Capacitor recognition has been done with an overall testing accuracy of 93.33%. © 2020 IEEE.

关键词： Printed circuit boards

Smart Prediction Models for Energy Efficiency in Smart Residential Buildings: A Deep Learning Approach

学校读者我要写书评

暂无评论

Smart Prediction Models for Energy Efficiency in Smart Resid...

Technological Engineering and its Applications in Sustainable Development (ICTEASD), International Conference for

作者： A. Vasantharaj M. Irshad Ahamed K. Prema Aditya Mudigonda J. B. Sapaev Kavitha Thandapani Electronics and Communication Engineering Kalaignar Karunanidhi Institute of Technology Information for Department of Electronics and Communication Engineerin E.G.S. Pillay Engineering College Nagapattinam Tamilnadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India JNIAS School of Planning and Architecture Hyderabad Telangana India Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University Tashkent Uzbekistan Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and vgy Technology Avadi Chennai Tamil Nadu

ISBN: (数字)9798350336474

ISBN: (纸本)9798350336481

Using power in houses has given rise to several ecological issues, including air pollution. Predicting building energy use is essential for better regulating or reducing energy usage. Machine Learning (ML) techniques have been used to estimate the power use of operating buildings. However, there has been little research on using ML algorithms to anticipate the prospective energy usage of buildings during the initial design phase. When lowering energy-inefficient buildings, it is crucial to tackle the underlying issue: accurately anticipating energy consumption before construction. This is necessary to prevent the future development of environmentally detrimental buildings. This research introduces a new and innovative Hybrid Deep Learning Model for Predicting Energy Efficiency in Smart Residential Buildings (HDL-PEE-SRB). The suggested framework has two steps: cleaning the information and constructing the model. The information cleansing step utilizes pre-processing methods to manipulate the original information and incorporates lag values as supplementary characteristics. During model-building, the hybrid model undergoes training using the processed data. The HDL model combines fully linked layers, Unidirectional Long Short-Term Memory (Uni-LSTM), and bi-directional LSTMs (Bi-LSTM), which are stacked together. The suggested model is assessed using standard energy usage databases, demonstrating higher accuracy than commonly used HDL models. The proposed model surpasses other HDL models, demonstrating the most favorable performance with a MAPE of 1.94% and an accuracy of 98.06%.

关键词： Deep learning Training Energy consumption Accuracy Biological system modeling Buildings Predictive models

Heliocentric Distance Dependence of Zodiacal Light Observed by Hayabusa2#

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tsumura, Kohji Matsuura, Shuji Sano, Kei Iwata, Takahiro Yano, Hajime Kitazato, Kohei Takimoto, Kohji Yamada, Manabu Morota, Tomokatsu Kouyama, Toru Hayakawa, Masahiko Yokota, Yasuhiro Tatsumi, Eri Matsuoka, Moe Sakatani, Naoya Honda, Rie Kameda, Shingo Suzuki, Hidehiko Cho, Yuichiro Yoshioka, Kazuo Ogawa, Kazunori Shirai, Kei Sawada, Hirotaka Sugita, Seiji Department of Natural Sciences Faculty of Science and Engineering Tokyo City University Tokyo158-8557 Japan Department of Physics School of Science and Technology Kwansei Gakuin University Hyogo669-1337 Japan Department of Space Systems Engineering School of Engineering Kyushu Institute of Technology Fukuoka804-8550 Japan Institute of Space and Astronautical Science Japan Aerospace Exploration Agency Kanagawa252-5210 Japan Department of Space and Astronautical Science The Graduate University of Advanced Studies Kanagawa240-0193 Japan Department of Computer Science and Engineering The University of Aizu Fukushima965-8580 Japan Planetary Exploration Research Center Chiba Institute of Technology Chiba275-0016 Japan Department of Earth and Planetary Science University of Tokyo Tokyo113-0033 Japan Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology Tokyo135-0064 Japan Instituto de Astrofisica de Canarias University of La Laguna Tenerife Spain Geological Survey of Japan National Institute of Advanced Industrial Science and Technology Ibaraki305-8567 Japan Center for Data Science Ehime University Ehime790-8577 Japan Rikkyo University Tokyo171-8501 Japan Meiji University Kanagawa214-8571 Japan Department of Complexity Science and Engineering University of Tokyo Chiba277-8561 Japan JAXA Space Exploration Center Japan Aerospace Exploration Agency Kanagawa252-5210 Japan Kobe University Hyogo657-8501 Japan

Zodiacal light (ZL) is sunlight scattered by interplanetary dust particles (IDPs) at optical wavelengths. The spatial distribution of IDPs in the Solar System may hold an important key to understanding the evolution of the Solar System and material transportation within it. The number density of IDPs can be expressed as n(r) ∼ r−α, and the exponent α ∼ 1.3 was obtained by previous observations from interplanetary space by Helios 1/2 and Pioneer 10/11 in the 1970s and 1980s. However, no direct measurements of α based on ZL observations from interplanetary space outside Earth’s orbit have been performed since then. Here, we introduce initial results for the radial profile of the ZL at optical wavelengths observed over the range 0.76-1.06 au by ONC-T aboard the Hayabusa2# mission in 2021-2022. The ZL brightness we obtained is well reproduced by a model brightness, although there is a small excess of the observed ZL brightness over the model brightness at around 0.9 au. The radial power-law index we obtained is α = 1.30 ± 0.08, which is consistent with previous results based on ZL observations. The dominant source of uncertainty arises from the uncertainty in estimating the diffuse Galactic light (DGL). © 2023, CC BY.

关键词： Orbits

Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ignatov, Andrey Timofte, Radu Chiang, Cheng-Ming Kuo, Hsien-Kai Xu, Yu-Syuan Lee, Man-Yu Lu, Allen Cheng, Chia-Ming Chen, Chih-Cheng Yong, Jia-Ying Shuai, Hong-Han Cheng, Wen-Huang Jia, Zhuang Xu, Tianyu Zhang, Yijian Bao, Long Sun, Heng Zhang, Diankai Gao, Si Liu, Shaoli Wu, Biao Zhang, Xiaofeng Zheng, Chengjian Lu, Kaidi Wang, Ning Sun, Xiao Wu, HaoDong Liu, Xuncheng Zhang, Weizhan Yan, Caixia Du, Haipeng Zheng, Qinghua Wang, Qi Chen, Wangdu Duan, Ran Duan, Ran Sun, Mengdi Zhu, Dan Chen, Guannan Cho, Hojin Kim, Steve Yue, Shijie Li, Chenghua Zhuge, Zhengyang Chen, Wei Wang, Wenxu Zhou, Yufeng Cai, Xiaochen Cai, Hengxing Xu, Kele Liu, Li Cheng, Zehua Lian, Wenyi Lian, Wenjing Computer Vision Lab ETH Zurich Switzerland AI Witchlabs Switzerland University of Wuerzburg Germany MediaTek Inc. Taiwan National Yang Ming Chiao Tung University Taiwan Video Algorithm Group Camera Department Xiaomi Inc. China Audio & Video Technology Platform Department ZTE Corp. China China School of Computer Science and Technology Xi'an Jiaotong University China MIGU Video Co. Ltd China BOE Technology Group Co. Ltd. China GenGenAI Korea Republic of North China University of Technology China Institute of Automation Chinese Academy of Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology China 4Paradigm Inc. Beijing China National University of Defense Technology Changsha China University of Oxford Oxford United Kingdom Uppsala University Sweden Northeastern University China

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of lowbitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt/30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper. Copyright © 2022, The Authors. All rights reserved.

关键词： Energy utilization

Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cichocki, Andrzej Tanaka, Toshihisa Cruces, Sergio Systems Research Institute of Polish Academy of Science Newelska 6 Warszawa01-447 Poland Gagarina 11 87-100Torun Poland Global Innovation Research Institute Tokyo University of Agriculture and Technology 2-24-16 Naka-cho Koganei-shi Tokyo Japan Riken AIP Nihonbashi 1 chome-4-1 Tokyo103-0027 Japan Department of Electrical Engineering and Computer Science Tokyo University of Agriculture and Technology 2-24-16 Naka-cho Koganei-shi Tokyo Japan Departamento de Teoria de la Senal y Comunicaciones Universidad de Sevilla Camino de los Descubrimientos s/n Seville41092 Spain

In this paper we propose and investigate a wide class of Mirror Descent updates (MD) and associated novel Generalized Exponentiated Gradient (GEG) algorithms by exploiting various trace-form entropies and associated deformed logarithms and their inverses - deformed (generalized) exponential functions. The proposed algorithms can be considered as extension of entropic MD and generalization of multiplicative gradient updates. In the literature, there exist nowadays over fifty mathematically well defined generalized entropies, so impossible to exploit all of them in one research paper. So, we focus only on several selected most popular entropies and associated logarithms like the Tsallis, Kaniadakis and Sharma-Taneja-Mittal and some of their extension like Tempesta or Kaniadakis-Scarfone entropies. The shape and properties of the deformed logarithms and their inverses are adjusted by one or more hyperparameters. By learning these hyperparameters, we can adapt to distribution of training data, which can be designed to the specific geometry of the optimization problem, leading to potentially faster convergence and better performance. The using generalized entropies and associated deformed logarithms in the Bregman divergence, used as a regularization term, provides some new insight into mirror descent and exponentiated gradient descent updates. © 2025, CC BY-NC-ND.

关键词： Exponential functions

Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Tianming Liu, Yang Liu, Xiaoyan Zhang, Hao Sharma, Gaurav Guo, Maozu The School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China The Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States The School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China The Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing100044 China

Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction. © 2021, CC BY.

关键词： Graphic methods