检索结果-内蒙古大学图书馆

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

作者： Polina Turishcheva Paul G. Fahey Michaela Vystrčilová Laura Hansel Rachel Froebe Kayla Ponder Yongrong Qiu Konstantin F. Willeke Mohammad Bashiri Ruslan Baikulov Yu Zhu Lei Ma Shan Yu Tiejun Huang Bryan M. Li Wolf De Wulf Nina Kudryashova Matthias H. Hennig Nathalie L. Rochefort Arno Onken Eric Wang Zhiwei Ding Andreas S. Tolias Fabian H. Sinz Alexander S. Ecker Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanford CA Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanford CA Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany and International Max Planck Research School for Intelligent Systems Tübingen Germany and Institute for Bioinformatics and Medical Informatics Tübingen University Germany lRomul Russia Institute of Automation Chinese Academy of Sciences China and Beijing Academy of Artificial Intelligence China Beijing Academy of Artificial Intelligence China Institute of Automation Chinese Academy of Sciences China The Alan Turing Institute UK and School of Informatics University of Edinburgh UK School of Informatics University of Edinburgh UK Centre for Discovery Brain Sciences University of Edinburgh UK and Simons Initiative for the Developing Brain University of Edinburgh UK Department of Neuroscience & Center for Neuroscience and Artificial Intelligence Baylor College of Medicine Houston Texas and Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine Stanford CA and Stanford Bio-X Stanford University Stanford CA and Wu Tsai Neurosciences Institute Stanford University Stanf

ISBN: (纸本)9798331314385

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different models on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the SENSORIUM 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 Competition Track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at ***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Gene Regulatory Interaction Networks and predicting therapeutic molecules for Hypopharyngeal Cancer and EGFR-mutated lung adenocarcinoma

arXiv

引用

arXiv 2024年

作者： Bhattacharjya, Abanti Islam, Md Manowarul Uddin, Md Ashraf Talukder, Md. Alamin Azad, A.K.M. Aryal, Sunil Paul, Bikash Kumar Tasnim, Wahia Abdulllah Almoyad, Muhammad Ali Moni, Mohammad Ali School of Information Technology Deakin University Waurn Ponds Campus Geelong Australia Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Department of Software Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh Riyadh13318 Saudi Arabia Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Bangladesh Department of Basic Medical Sciences College of Applied Medical Sciences King Khalid University Saudi Arabia Artificial Intelligence & Data Science Faculty of Health and Behavioural Sciences The University of Queensland Australia

With the advent of Information technology, the Bioinformatics research field is becoming increasingly attractive to researchers and academicians. The recent development of various Bioinformatics toolkits has facilitated the rapid processing and analysis of vast quantities of biological data for human perception. Most studies focus on locating two connected diseases and making some observations to construct diverse gene regulatory interaction networks, a forerunner to general drug design for curing illness. For instance, Hypopharyngeal cancer is a disease that is associated with EGFR-mutated lung adenocarcinoma. In this study, we select EGFR-mutated lung adenocarcinoma and Hypopharyngeal cancer by finding the Lung metastases in hypopharyngeal cancer. To conduct this study, we collect Mircorarray datasets from GEO (Gene Expression Omnibus), an online database controlled by NCBI. Differentially expressed genes, common genes, and hub genes between the selected two diseases are detected for the succeeding move. Our research findings have suggested common therapeutic molecules for the selected diseases based on 10 hub genes with the highest interactions according to the degree topology method and the maximum clique centrality (MCC). Our suggested therapeutic molecules will be fruitful for patients with those two diseases simultaneously. © 2024, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function

arXiv

引用

arXiv 2023年

作者： Liu, Liu Liu, Xuanqing Hsieh, Cho-Jui Tao, Dacheng Institute of Artificial Intelligence State Key Lab of Software Development Environment Beihang University China University of California Los Angeles United States School of Computer Science Sydney AI Centre Faculty of Engineering the University of Sydney SydneyNSW2008 Australia

Trust-region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for non-convex optimization by concurrently computing function value, gradient, and Hessian matrix to obtain the next search direction and the adjusted parameters. Although stochastic approximations help largely reduce the computational cost, it is challenging to theoretically guarantee the convergence rate. In this paper, we explore a family of stochastic TR and ARC methods that can simultaneously provide inexact computations of the Hessian matrix, gradient, and function values. Our algorithms require much fewer propagations overhead per iteration than TR and ARC. We prove that the iteration complexity to achieve ǫ-approximate second-order optimality is of the same order as the exact computations demonstrated in previous studies. Additionally, the mild conditions on inexactness can be met by leveraging a random sampling technology in the finite-sum minimization problem. Numerical experiments with a non-convex problem support these findings and demonstrate that, with the same or a similar number of iterations, our algorithms require less computational overhead per iteration than current second-order methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Communication Induced Checkpointing based Fault Tolerance Mechanism – A Review and CIAC-FTM Framework in IoT Environment

Communication Induced Checkpointing based Fault Tolerance Me...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： A Sowjanya Lakshmi Ch Vani Priya Gaurav Gupta Information Science and Engineering Sir. M. Visvesvaraya Institute of Technology Bengaluru India Yogananda School of Artificial Intelligence Computer and Data Sciences Shoolini University Solan Himachal Pradesh India

ISBN: (纸本)9781665462013

High performance computations in IoTsystems processes huge data, suffers from various types of faults due to hardware or software faults, malicious attacks, network congestion, missing deadlines and server overloads, and Fault Tolerance in such systems is mandatory to maintain the performance of long running *** Induced Adaptive Checkpointing Fault Tolerance Mechanism (CIAC-FTM) used to address such Faults. The research focus on Software Faults - Transient Faults at application level. This CIAC-FTM places checkpoints at required nodes depending on the type of fault detected, in turn reduces checkpoints and storage overheads. The collaboration of Sensors, huge data, Machine to Machine (M2M) communication,and IoT gives us a promising formula for near perfect system. Current technologies are able to work hand-in-hand to create a bigger system. IoT ensures a more connected world. The data procured by the sensor nodes are pushed into a network and processing units, processed data used to take decision to act on actuators as designed. Fault-free data at every transaction is at most priority and so Communication Induced Checkpoints (CIC)areintroduced to ensure that the fault-free task restarts and hence CIAC-FTM ensure that the transient faults are rectified.

关键词： Checkpointing Fault tolerance Adaptive systems Fault tolerant systems Software Sensor systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Learning superconductivity from ordered and disordered material structures 24

Learning superconductivity from ordered and disordered mater...

引用

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

作者： Pin Chen Luoxuan Peng Rui Jiao Qing Mo Zhen Wang Wenbing Huang Yang Liu Yutong Lu National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University Dept. of Comp. Sci. & Tech. Institute for AI BNRist Center Tsinghua University and Institute for AIR Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9798331314385

Superconductivity is a fascinating phenomenon observed in certain materials under certain conditions. However, some critical aspects of it, such as the relationship between superconductivity and materials' chemical/structural features, still need to be understood. Recent successes of data-driven approaches in material science strongly inspire researchers to study this relationship with them, but a corresponding dataset is still lacking. Hence, we present a new dataset for data-driven approaches, namely SuperCon3D, containing both 3D crystal structures and experimental superconducting transition temperature (Tc) for the first time. Based on SuperCon3D, we propose two deep learning methods for designing high Tc superconductors. The first is SODNet, a novel equivariant graph attention model for screening known structures, which differs from existing models in incorporating both ordered and disordered geometric content. The second is a diffusion generative model DiffCSP-SC for creating new structures, which enables high Tc-targeted generation. Extensive experiments demonstrate that both our proposed dataset and models are advantageous for designing new high Tc superconducting candidates.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Generalization of Multi-Source Fusion-Based Framework to Stock Selection

SSRN

引用

SSRN 2023年

作者： Snášel, Václav Velasquez Silva, Juan Domingo Pant, Millie Georgiou, Dimitrios Kong, Lingping Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Czech Republic Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India Departament of Industrial Engineering University of Chile Santiago Chile Faculty of Electrical Engineering and Computer Science National Technical University of Athens Greece Chile Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India

Selecting outstanding tech stocks for investment is challenging. Specifically, studying the investment for academic purposes is not mature enough due to the disarray of the publications and the `over' informative experience from profit-making websites. Often some authors entitle stock price prediction subject as a stock selection problem;both prediction and selection are just sub-section of portfolio management. Moreover, stock websites provide tons of potential criteria showing their perspective evaluation to simulate and monitor the stock market professionally, which causes an extra problem for academic studies screening out the less informative criteria. The paper generalizes a novel framework with a user-interactive interface for stock selection problems based on multi-source data fusion and decision-level fusion to enhance reliability that is limited by the narrow criteria performance and to enhance the strength of a model overcoming the weakness of a single-performed model. This framework benefits the time-series prediction and decision-making study. Besides, we propose adopting dynamic time warping to assist a task-learning process by customizing a loss function that improves the accuracy of data prediction. The experiment shows that the proposed method reduces the prediction log error by 28\% in a best case of real-situation data and decreases the warping cost by 20\%. Finally, we illustrate the proposed framework by implementing it in a real-world stock data selection. The results are practical and effective, further justified through a detailed ablation study. © 2023, The Authors. All rights reserved.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Exploiting Deep Learning Architectures for Effective Real-Time data Analysis in Machine Learning

Exploiting Deep Learning Architectures for Effective Real-Ti...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Shreenidhi H S S. Rajarajeswari Suvarna R. Bhagwat Khushboo Sharma Kanika Seth Rakesh Kumar Yadav Department of Computer Science Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Ramnagar Karnataka India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Electrical Engineering Vivekananda Global University Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

This paper seeks to discover how deep state-of-the-art architectures can be leveraged for robust actual-time information evaluation in device studying packages. The paper begins by supplying a comprehensive assessment of contemporary the modern-day in deep brand new-based totally facts evaluation technology. It then examines case research state-of-the-art real-time records analysis programs to illustrate the viability and blessings of modern-day existing deep latest architectures. Programs encompass self-driving vehicle generation, laptop vision, natural language processing, and time-collection evaluation. This targeted evaluation is supplemented by assessing ultra-modern capability shortcomings and demanding situations associated with using these architectures in actual-time scenarios. Subsequently, the paper provides a set of modern-day pointers and first-rate practices to help practitioners efficiently leverage deep trendy architectures for actual-time information evaluation. With the aid of combining a comprehensive review of current deep-gaining knowledge state modern-based records evaluation technology, a detailed dialogue present day its utility guiding ideas, and a summary of the latest potential shortcomings and demanding situations, this paper offers a practical manual to the effective of deep learning architectures for real-time data analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive evaluation method of driving behavior based on neural network 4

Comprehensive evaluation method of driving behavior based on...

引用

2021 4th International Conference on computer Information science and Application Technology, CISAT 2021

作者： Li, Jiayao Li, Li Jiao, Ge Zhao, Xianjing He, Yuhong College of Computer Science and Technology Hengyang Normal University Hunan Hengyang China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing University of Education Chongqing China Artificial Intelligence and Big Data College Chongqing College of Electronic Engineering Chongqing China

In recent years, the number of traffic accidents in the world has increased sharply. Reasonable mining of the OBD data generated in the process of vehicle driving will help to improve traffic safety. However, the existing driving behavior scoring models have the following shortcomings: the indexes are not comprehensive enough, and the selection of weights is not objective. In order to solve these shortcomings, this paper proposes 16 driving behavior indexes and related definitions;the neural network is used to construct the model to distribute the weight reasonably;a new comprehensive evaluation model of driving behavior is constructed. The feasibility and efficiency of the model are verified by experiments on real vehicle OBD data sets. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 Licence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Long Short-Term Memory Units for Time Series Forecasting

Using Long Short-Term Memory Units for Time Series Forecasti...

引用

International Conference on Futuristic Technologies (INCOFT)

作者： Dhyan Yadav Laxman Sahoo Sanjeev Kumar Mandal G. Ravivarman P. Vijayaraghavan Prasad B Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore Karnataka India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India

This paper specializes in using long short-time period memory (LSTM) networks for time collection forecasting. LSTM is a form of artificial recurrent neural network (RNN) that is especially properly-applicable to analyze from enjoy over long sequences of statistics. Not like conventional recurrent networks, LSTM networks can technique input sequences in each instruction, while also allowing for the protection of lengthy-time period dependencies and rapid convergence. It's far shown that these characteristics of LSTM networks allow them to be used efficaciously for forecasting time series consisting of inventory performance and electricity tendencies. Strategies inclusive of feeding the LSTM network data in a time step layout, the use of peephole connections, stacking a couple of layers and early stopping are discussed. Results are then presented and mentioned, demonstrating that LSTM networks can research complex lengthy-time period dependencies in time series facts and correctly forecast destiny values.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bipartite Flocking Control for Multi-Agent Systems with Switching Topologies and Time Delays Under Coopetition Interactions

Bipartite Flocking Control for Multi-Agent Systems with Swit...

引用

IEEE Conference on Decision and Control

作者： Zhuangzhuang Ma Bowen Li Jinliang Shao Yuhua Cheng Wei Xing Zheng School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China School of Computer Data and Mathematical Sciences Western Sydney University Sydney NSW Australia

This paper investigates the bipartite flocking behavior of multi-agent systems with coopetition interactions, where communications between agents are described by signed digraphs. The scenario with switching topologies due to the movement of agents, and time delays caused by the limited data transmission capability, is considered comprehensively. Nonlinear weight functions are designed to describe the relationship between the communication distance of agents and the coopetition degree in real biological networks. A distributed update rule based on the neighbors' information and the designed weight functions is proposed. By the aid of the graph theory and sub-stochastic matrix properties, the effectiveness of the proposed update rule is proved theoretically, and the algebraic conditions for achieving the bipartite flocking behavior are obtained. Finally, the theoretical results are verified by numerical simulations.

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：