检索结果-内蒙古大学图书馆

International conference on Intelligent Sustainable Systems (ICISS)

作者： Mohan, Abishaik Raju, R. Deepak Janarthanan, P. Sri Venkateswara Coll Engn Dept CSE Sriperumbudur India

ISBN: (纸本)9781538677995

Livestock breeding farms are commonly found to be geographically distributed in remote areas with comparatively poor conditions of disease diagnosis. Usually, it is difficult to perform animal disease diagnosis quickly and concisely due to the technical expertise and experience required. But, the farms can diagnose these diseases precisely using the animal disease diagnosis expert system(ADDES) which could ascertain a proper enlargement of the stockbreeding industry. In this paper, we are trying to enhance the diagnosis accuracy and minimize the loss by proposing a method using Convolutional neural network(CNN). Our center of attention is on evolving an effective strategy for this diagnosis issue by improvising the existing techniques. By segmenting and extracting the features from the diseased images dynamically, our model is bound to produce an accurate result. We evaluate our algorithms via experiments and through the visualization of these rules and plots, one can accurately come up with an elaborate explanation of the disease and its cause and cure more effectively.

关键词： Convolutional neural networks Expert System Image processing Stockbreeding and Visualization

来源：评论

学校读者我要写书评

暂无评论

Towards crowdsourced training of large neural networks using decentralized mixture-of-experts 20

Towards crowdsourced training of large neural networks using...

引用

Proceedings of the 34th International conference on neural Information processing Systems

作者： Max Ryabinin Anton Gusev Yandex National Research University Higher School of Economics Independent

ISBN: (纸本)9781713829546

Many recent breakthroughs in deep learning were achieved by training increasingly larger models on massive datasets. However, training such models can be prohibitively expensive. For instance, the cluster used to train GPT-3 costs over $250 million. As a result, most researchers cannot afford to train state of the art models and contribute to their development. Hypothetically, a researcher could crowdsource the training of large neural networks with thousands of regular PCs provided by volunteers. The raw computing power of a hundred thousand $2500 desktops dwarfs that of a $250M server pod, but one cannot utilize that power efficiently with conventional distributed training methods. In this work, we propose Learning@home: a novel neural network training paradigm designed to handle large amounts of poorly connected participants. We analyze the performance, reliability, and architectural constraints of this paradigm and compare it against existing distributed training techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing 2D Representation via Adjacent Views for 3D Shape Retrieval 17

Enhancing 2D Representation via Adjacent Views for 3D Shape ...

引用

IEEE/CVF International conference on Computer Vision (ICCV)

作者： Xu, Cheng Li, Zhaoqun Qiu, Qiang Leng, Biao Jiang, Jingfei Beihang Univ Sch Comp Sci & Engn Beijing Peoples R China Duke Univ Durham NC 27706 USA Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781728148038

Multi-view shape descriptors obtained from various 2D images are commonly adopted in 3D shape retrieval. One major challenge is that significant shape information is discarded during 2D view rendering through projection. In this paper, we propose a convolutional neural network based method, Neighbor-Center Enhanced network, to enhance each 2D view using its neighboring ones. By exploiting cross-view correlations, Neighbor-Center Enhanced network learns how adjacent views can be maximally incorporated for an enhanced 2D representation to effectively describe shapes. We observe that a very small amount of, e.g., six, enhanced 2D views, are already sufficient for panoramic shape description. Thus, by simply aggregating features from six enhanced 2D views, we arrive at a highly compact yet discriminative shape descriptor. The proposed shape descriptor significantly outperforms state-of-the-art 3D shape retrieval methods on the ModelNet and ShapeNet-Core55 benchmarks, and also exhibits robustness against object occlusion.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Geryon: Accelerating distributed CNN Training by network-Level Flow Scheduling

Geryon: Accelerating Distributed CNN Training by Network-Lev...

引用

IEEE Annual Joint conference: INFOCOM, IEEE Computer and Communications Societies

作者： Shuai Wang Dan Li Jinkun Geng Department of Computer Science and Technology Tsinghua University China

ISBN: (数字)9781728164120

ISBN: (纸本)9781728164137

Increasingly rich data sets and complicated models make distributed machine learning more and more important. However, the cost of extensive and frequent parameter synchronizations can easily diminish the benefits of distributed training across multiple machines. In this paper, we present Geryon, a network-level flow scheduling scheme to accelerate distributed Convolutional neural network (CNN) training. Geryon leverages multiple flows with different priorities to transfer parameters of different urgency levels, which can naturally coordinate multiple parameter servers and prioritize the urgent parameter transfers in the entire network fabric. Geryon requires no modification in CNN models and does not affect the training accuracy. Based on the experimental results of four representative CNN models on a testbed of 8 GPU servers, Geryon achieves up to 95.7% scaling efficiency even with 10GbE bandwidth. In contrast, for most models, the scaling efficiency of vanilla TensorFlow is no more than 37% and that of TensorFlow with parameter partition and slicing is around 80%. In terms of training throughput, Geryon enhanced with parameter partition and slicing achieves up to 4.37x speedup, where the flow scheduling algorithm itself achieves up to 1.2x speedup over parameter partition and slicing.

关键词： Training Computational modeling Bandwidth Graphics processing units Processor scheduling Throughput Acceleration

来源：评论

学校读者我要写书评

暂无评论

MapReduce-Based Convolutional neural network for Text Categorization 11th

MapReduce-Based Convolutional Neural Network for Text Catego...

引用

11th International conference on Computational Collective Intelligence (ICCCI)

作者： Ferjani, Eman Hidri, Adel Sassi Hidri, Minyar Frihida, Ali Imam Abdulrahman Bin Faisal Univ Deanship Preparatory Year & Supporting Studies Dammam Saudi Arabia Tunis El Manar Univ Natl Engn Sch Tunis Tunis Tunisia

ISBN: (纸本)9783030283742;9783030283735

Convolutional neural network (CNN) is an algorithm among deep learning. It is an effective method of solving common Natural Language processing tasks such as text categorization. In this paper, we investigate the text categorization problem using a deep learning approach in particular CNN method. However, due to the rise of Big Data and increased complexity of tasks, the efficiency of CNNs have been severely impacted because of their extensive training time and high computational cost. To overcome these obstacles, we propose a MapReducebased CNN by reformulating the CNN's training from a single training network to a series of parallel trained smaller networks. Each smaller network processes a sub-sample of input text.

关键词： distributed text representation CNN Word2vec MapReduce Text categorization

来源：评论

学校读者我要写书评

暂无评论

2019 5th International conference on Image Information processing, ICIIP 2019

2019 5th International Conference on Image Information Proce...

引用

5th International conference on Image Information processing, ICIIP 2019

ISBN: (纸本)9781728108988

The proceedings contain 112 papers. The topics discussed include: image encryption method using differential expansion technique, AES and RSA algorithm;recognition of Kannada characters in scene images using neural networks;a light weighted deep learning framework for multiple sclerosis lesion segmentation;implementation of distributed file storage and access framework using IPFS and blockchain;video steganography technique in uncompressed raw domain based on transform domain and using SSVLCs;deep learning approach for automatic classification of x-ray images using convolutional neural network;internet of things for precision agriculture applications;and a secure audio steganography scheme using genetic algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Driving Assistance System using distributed computation on single-board computers 7

Advanced Driving Assistance System using distributed computa...

引用

7th International conference on Robotics and Mechatronics (ICRoM)

作者： Abrinia, Karen Ayati, Moosa Shirvan, Hadi Niknam Abazari, Amin Tabrizi, Ali Haddad Shahbazzadeh, Mostafa Maroufi, Zeinab Akrami, Mohammadreza Safaee, Erfan Fasakhodi, Amirhossein Oliaei Panahi, Amirhossein Univ Tehran Sch Mech Engn Tehran Iran Univ Tehran Fac New Sci & Technol Dept Mechatron Engn Tehran Iran Univ Tehran Dept New Sci & Technol Tehran Iran

ISBN: (纸本)9781728166049

Due to increasing use of vehicles and road traffic, drive safety has become an important issue. Therefore, an Advanced Driving Assistant System (ADAS) can be a convenient option to increase driving safety. This paper presents a model of an ADAS that is capable of driving from one place to another in different paths such as curved, straight and straight line followed by curved lines. This area of research is divided into several sub-domains, such as deep learning, hardware platform, computer vision, and control. Every self-driving car must be aware of its surroundings and act accordingly. Advances in neural networks and deep learning made it possible to extract information from cameras easily and robustly. In this paper, a neural network is trained to identify various objects such as traffic lights and pedestrians. In addition, image processing is used to detect road lines. due to high computational costs of image processing operations, a network of embedded systems are utilized. Furthermore, MPC control method is used for automated and intelligent steering that makes the right decisions in a timely manner with a small error.

关键词： ADAS Self-Driving cars Deep Learning TensorFlow Object Detection Classification embedded systems

来源：评论

学校读者我要写书评

暂无评论

neural network based soft sensor for pilot-plant distillation column 22

Neural network based soft sensor for pilot-plant distillatio...

引用

22nd Topical conference on Refinery processing 2019 - Topical conference at the 2019 AIChE Spring Meeting and 15th Global Congress on Process Safety

作者： Abdulla, Thaer A. Osman, Mohanad Edgar, Thomas F. University of Texas at Austin AustinTX United States Canadian Natural Resources Limited CalgaryAB Canada

ISBN: (纸本)9781510886773

The development of an inferential soft sensor for a pilot-plant distillation column separating an ethanol-water mixture using neural network (NN) method has been investigated in this work. Inferential sensors are increasingly used in the process industries to infer the value of the main quality variable while utilizing much easier to measure secondary variables of the process. The lags between the input variables and the output variable vary due to changes in operating conditions. Previous studies have introduced different methods to estimate lags for input and output variables, but all of them have assumed these lags to be constant regardless of the changes in the operating conditions. In this work, an inferential sensor that can infer the composition of ethanol at the top product using time lags for the input variables and varied first-order time constant lags with the output variable is developed. The developed inferential sensor is based on a neural network (NN) model. This NN model is built in MATLAB/Simulink. An OPC link is established in order to communicate between MATLAB/Simulink and the Emerson DetlaV distributed Control System (DCS) of the pilot-plant distillation column. Principal Component Analysis (PCA) and Projection to Latent Structures (PLS) methods are used in this work to remove the outliers from the input variables set and to determine the most correlated values of the input variables and their lags with the output variable Xa (ethanol mole fraction of distillate product) respectively. The model adaptively selects the correct first-order time constant lags of an output variable according to the instantaneous operating condition (the composition of ethanol is increased or decreased) and assigns a best value for each case. The prediction performance of the proposed NN models (with and without time lags for input variables) is illustrated using experimental data from the pilot-scale ethanol-water distillation column. More than 400 samples were colle

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Smart Approach to Build A Deep neural network Based IDS for Cloud Environment Using an Optimized Genetic Algorithm 19

Smart Approach to Build A Deep Neural Network Based IDS for ...

引用

2nd International conference on networking, Information Systems and Security (NISS)

作者： Chiba, Zouhair Abghour, Noreddine Moussaid, Khalid El Omri, Amina Rida, Mohamed Hassan II Univ Casablanca Fac Sci LIMSAD Labs Casablanca 20100 Morocco

ISBN: (纸本)9781450366458

In recent years cloud computing has revolutionized the IT world with rapidly emerging and widely accepted paradigm for computing systems, and it has become popular among users in organizations and companies. Nowadays, numerous organizations have begun to upload their massive amount of prominent data into public cloud. Nevertheless, uploading sensitive data to open and distributed public cloud storage services poses security risks such as availability, confidentiality and integrity to organizations. Moreover, non-stop cloud services have caused high levels of intrusion and abuse. Thereby, protecting network accessible Cloud resources and services from various threats and attacks is of great concern. To address this issue, it is imperative to develop a powerful network Intrusion System (NIDS) to detect both outsider and insider intruders with high detection precision in the cloud environment. In this work, we propose a smart approach using an Improved Genetic Algorithm (IGA) to build a Deep neural network (DNN) based anomaly NIDS. Genetic Algorithm (GA) is improved through optimization strategies, namely Parallel processing and Fitness Value Hashing, which reduce execution time, convergence time and save processing power. Our approach consists to use IGA in order to search the optimal or near optimal combination of most relevant values of the parameters included in construction of DNN based IDS or impacting its performance, like feature selection, data normalization, architecture of DNN, activation function, learning rate and Momentum term, which ensure high detection rate, high accuracy and low false alarm rate. CloudSim 4.0 simulator platform and CICIDS 2017 benchmark dataset were used for simulation and validation of the proposed system. The experimental results obtained demonstrate that in comparison to several traditional and recent approaches, our proposed IDS achieves higher detection rate and lower false positive rate.

关键词： Cloud computing network intrusion detection system Anomaly detection Deep neural network Back propagation learning algorithm Optimization Genetic algorithm CICIDS2017 dataset

来源：评论

学校读者我要写书评

暂无评论

A robust multi-batch L-BFGS method for machine learning*

引用

OPTIMIZATION METHODS & SOFTWARE 2020年第1期35卷 191-219页

作者： Berahas, Albert S. Takac, Martin Lehigh Univ Dept Ind & Syst Engn Bethlehem PA 18015 USA

This paper describes an implementation of the L-BFGS method designed to deal with two adversarial situations. The first occurs in distributed computing environments where some of the computational nodes devoted to the evaluation of the function and gradient are unable to return results on time. A similar challenge occurs in a multi-batch approach in which the data points used to compute function and gradients are purposely changed at each iteration to accelerate the learning process. Difficulties arise because L-BFGS employs gradient differences to update the Hessian approximations, and when these gradients are computed using different data points the updating process can be unstable. This paper shows how to perform stable quasi-Newton updating in the multi-batch setting, studies the convergence properties for both convex and non-convex functions, and illustrates the behaviour of the algorithm in a distributed computing platform on binary classification logistic regression and neural network training problems that arise in machine learning.

关键词： L-BFGS multi-batch fault-tolerant sampling consistency overlap

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：