检索结果-内蒙古大学图书馆

10th International conference on Cyber-Enabled distributed Computing and Knowledge Discovery (CyberC)

作者： Long, Weibing Zhang, Kunli Ma, Hongchao Yue, Donghui Zhuang, Lei Zhengzhou Univ Sch Informat Engn Zhengzhou Henan Peoples R China

ISBN: (数字)9781728109749

ISBN: (纸本)9781728109749

The data-driven medical health information processing has become a new development direction, especially the auxiliary diagnosis based on the electronic medical records (EMRs), which is of great significance to improve population health. In this paper, to obtain excellent obstetric auxiliary diagnostic results, the Chinese obstetric EMRs is analyzed and processed, and finally the auxiliary diagnosis task is transformed into a multi-label classification problem. Moreover, two effective global error functions arc proposed by enhancing pairwise labels discrimination to improve the Backpropagation for Multi-label Learning (BP-MLL) that depends on the neural network model. The experiment results of some public multi-label datasets and the Chinese obstetric dataset show that the two error functions have better overall performance compared with BP-MLL original error function and some well-established multi-label learning algorithms.

关键词： auxiliary diagnosis neural network pairwise labels discrimination multi-label learning Chinese obstetric EMRs

来源：评论

学校读者我要写书评

暂无评论

Applying the Artificial neural networks with Multiwavelet Transform on Phoneme recognition

引用

Journal of Physics: conference Series 2021年第1期1804卷

作者： Baydaa Jaffer AlKhafaji May A. Salih Shaymaa AbdulHussein Shnain Omar Adel Rashid Abdulla Adil Rashid Moheeb Tariq Hussein Computer Science Department College of Education for Pure Science/Ibn Al-Haitham University of Baghdad Iraq. Math and Computer Science Department Basic Education College University of Babylon Hilla Iraq

There are several advantages of Phoneme recognition. identification. It is easier to use speech for data entrance spoken communication for data ingress than other tools. It allows writing user-friendly data entrance exploiter-friendly data ingress programs. There are several difficulties in speech voice communication recognition. One of these difficulties is noise. Variability in speech is another problem. Even the speech of same speaker varies. The ability of artificial neural networks to generalize and optimize more quickly than some conventional algorithms algorithmic rule has been observed in different areas of research inquiry such as speech and pattern convention recognition, financial forecasting prognostication, image data compression and noise reduction simplification in signal processing. neural networks take advantage of the redundancy incorporated in their distributed processing structures the proposed system depends on Artificial neural networks network as decision making qualification algorithm to find the best match peer for the tested phonemes. Phoneme. The data used in this project are Arabic phonemes language phoneme stored as 8-bit mono infectious mononucleosis 8000Hz PCM WAVE Sound Auditory sensation file. The results showed that the accuracy of the proposed system is 98% recognizes the phonemes efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Recognition with MapReduce Based Convolutional neural networks

Image Recognition with MapReduce Based Convolutional Neural ...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication conference (UEMCON)

作者： Jackie Leung Min Chen State University of New York New Paltz NY USA

ISBN: (纸本)9781728138862

Convolutional neural networks (CNNs) have gained global recognition in advancing the field of artificial intelligence and have had great successes in a wide array of applications including computer vision, speech and natural language processing. However, due to the rise of big data and increased complexity of tasks, the efficiency of training CNNs have been severely impacted. To achieve state-of-art results, CNNs require tens to hundreds of millions of parameters that need to be fine-tuned, resulting in extensive training time and high computational cost. To overcome these obstacles, this work takes advantage of distributed frameworks and cloud computing to develop a parallel CNN algorithm. Close examination of the implementation of MapReduce based CNNs as well as how the proposed algorithm accelerates learning are discussed and demonstrated through experiments. Results reveal high accuracy in classification and improvements in speedup, scaleup and sizeup compared to the standard algorithm.

关键词： cloud computing computer vision convolutional neural nets data handling image recognition learning (artificial intelligence) natural language processing parallel processing Image recognition Cloud Computing data processing images computer vision Natural Language processing PARALLEL processing (COMPUTERS) neural network big data

来源：评论

学校读者我要写书评

暂无评论

Anti-synchronization of neural networks with Mixed Delays 25th

Anti-synchronization of Neural Networks with Mixed Delays

引用

25th International conference on neural Information processing (ICONIP)

作者： Liu, Dan Ye, Dan Northeastern Univ Coll Informat Sci & Engn Shenyang 110189 Liaoning Peoples R China

ISBN: (纸本)9783030041793;9783030041786

This paper focuses on the anti-synchronization of neural networks (NNs) with mixed delays. Under state feedback control, by establishing suitable Lyapunov functional and applying inequality techniques, corresponding algebraic conditions are given to ascertain anti-synchronization of drive-response NNs with time-varying delays and unbounded distributed delays. The availability of the proposed result is verified by an example.

关键词： neural networks Anti-synchronization Mixed delays

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: Robustly Executing DNNs in IoT Systems Using Coded distributed Computing ∗

Late Breaking Results: Robustly Executing DNNs in IoT System...

引用

Design Automation conference

作者： Ramyad Hadidi Jiashen Cao Michael S. Ryoo Hyesoon Kim GeorgiaTech Google Brain

ISBN: (纸本)9781728124261

Internet of Things (IoT) devices have access to an abundance of raw data for processing. With deep neural networks (DNNs), not only the demand for the computing power of IoT devices is increasing, but also privacy concerns are motivating the importance of close-to-edge computation. DNN execution by distributing its computation is common in IoT systems. However, managing unstable latencies in a network and intermittent failures are serious challenges. Our work provides robustness and close-to-zero recovery latency by adapting coded distributed computing (CDC). We analyze robust execution on a mesh of Raspberry Pis by studying four DNNs.

关键词： Performance evaluation Robustness Internet of Things Computational modeling Data models neural networks

来源：评论

学校读者我要写书评

暂无评论

distributed Deep Reinforcement Learning using TensorFlow 3

Distributed Deep Reinforcement Learning using TensorFlow

引用

3rd International conference on Current Trends in Computer, Electrical, Electronics and Communication, CTCEEC 2017

作者： Ajay Rao, P. Navaneesh Kumar, B. Cadabam, Siddharth Praveena, T. Department of Computer Science Engineering RVCE Bengaluru 59 India

ISBN: (纸本)9781538632420

Deep Reinforcement Learning is the combination of Reinforcement Learning algorithms with Deep neural network, which had recent success in learning complicated unknown environments. The trained model is a Convolutional neural network trained using Q-Learning Loss value. The agent takes in observation, i.e. raw pixel image and reward from the environment for each step as input. The deep Q-learning algorithm gives out the optimal action for every observation and reward pair. The hyperparameters of Deep Q-network remain unchanged for any environment. TensorFIow, an open source machine learning and numerical computation library is used to implement the deep Q-Learning algorithm on GPU. The distributed TensorFIow architecture is used to maximize the hardware resource utilization and reduce the training time. The usage of Graphics processing Unit (GPU) in the distributed environment accelerated the training of deep Q-network. On implementing the deep Q-learning algorithm for many environments from OpenAI Gym, the agent outperforms a decent human reference player with few days of training. © 2017 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection 19

Comparison of Deep Learning and the Classical Machine Learni...

引用

19th IEEE/ACIS International conference on Software Engineering, Artificial Intelligence, networking and Parallel/distributed Computing (SNPD)

作者： Sewak, Mohit Sahay, Sanjay K. Rathore, Hemant BITS Dept CS & IS Goa Campus Pilani Rajasthan India

ISBN: (纸本)9781538658895

Recently, Deep Learning has been showing promising results in various Artificial Intelligence applications like image recognition, natural language processing, language modeling, neural machine translation, etc. Although, in general, it is computationally more expensive as compared to classical machine learning techniques, their results are found to be more effective in some cases. Therefore, in this paper, we investigated and compared one of the Deep Learning Architecture called Deep neural network (DNN) with the classical Random Forest (RF) machine learning algorithm for the malware classification. We studied the performance of the classical RF and DNN with 2, 4 & 7 layers architectures with the four different feature sets, and found that irrespective of the features inputs, the classical RF accuracy outperforms the DNN.

关键词： Malware Deep Learning Machine Learning Auto Encoders Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Beacon: Image Storage and Broadcast over BLE Using Variational Autoencoder Generative Adversarial network 14

Deep Beacon: Image Storage and Broadcast over BLE Using Vari...

引用

14th Annual International conference on distributed Computing in Sensor Systems (DCOSS)

作者： Shao, Chong Nirjon, Shahriar Univ North Carolina Dept Comp Sci Chapel Hill NC 27599 USA

ISBN: (纸本)9781538654705

This paper describes Deep Beacon which uses a set of cheap, low-power, storage-constrained Bluetooth Low Energy (BLE) devices to beacon (i.e. broadcast) a color image over a very long period (months, as opposed to days or weeks). The system employs deep neural network image encoder to encode a given input image and generates an extremely compact representation (as small as 10 bytes) of the image. At the receiver end, another deep neural network decoder runs on a mobile device which decodes (i.e. generates) the original image from the BLE broadcast messages. We evaluate Deep Beacon's performance using hand-written digit images and different types of RGB images that contain objects such as birds, flowers, and traffic signs. We empirically determine the tradeoffs between the system lifetime and the quality of broadcast images, and determine an optimal set of parameters for our system, under user-specified constraints such as the number of available beacon devices, maximum latency, and life expectancy. We develop a smartphone application that takes an image and user-requirements as inputs, shows previews of different quality output images, writes the encoded image into a set of beacons, and reads the broadcasted image back. Our evaluation shows that one beacon device is capable of broadcasting high-quality images (90% structurally similar to original images) for a year-long continuous broadcasting, and both the lifetime and the image quality improve when two beacons are used.

关键词： BLE deep learning image processing

来源：评论

学校读者我要写书评

暂无评论

Pipe-Torch: Pipeline-Based distributed Deep Learning in a GPU Cluster with Heterogeneous networking

Pipe-Torch: Pipeline-Based Distributed Deep Learning in a GP...

引用

International conference on Advanced Cloud and Big Data (CBD)

作者： Jun Zhan Jinghui Zhang Southeast University NanJing China

Because training a deep neural network (DNN) takes arduous amounts of time and computation, often researchers expedite the training process via distributed parallel training on GPUs. On one hand, this lower computing-to-communication ratio makes traditional data parallelism difficult to scale, and traditional model parallelism leads to low GPU utilization. Both make it difficult to obtain a higher speedup. On the other hand, multi-GPU systems exhibit complex connectivity among GPUs. Overall, workload schedulers must consider hardware topology and workload communication requirements to allocate GPU resources for optimal execution time and improved utilization in GPU clusters with heterogeneous networking. Thus, in this paper, we introduce Pipe-torch, an improved pipeline-hybrid parallelism method (using both data and model parallelism) in a heterogeneous network environment. Ultimately, the framework's model partition algorithm aims to expedite pipeline-hybrid parallelism training between heterogeneous network-connected GPUs. Experiments with four different DNN models show that Pipetorch averages 1.4x speedup compared to data parallelism.

关键词： Graphics processing units Training Parallel processing Computational modeling Data models Pipelines Load modeling

来源：评论

学校读者我要写书评

暂无评论

distributed DNN Based User Association and Resource Optimization in mmWave networks

Distributed DNN Based User Association and Resource Optimiza...

引用

IEEE Global Communications conference

作者： Haisen Zhang Haijun Zhang Wei Huangfu Wei liu Jiangbo Dong Keping long Arumugam Nallanathan Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China China Mobile Group Design Institute Co. Ltd Beijing China Queen Mary University of London London U.K.

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Millimeter wave (mmWave) communication technology has become an attractive solution to meet exponential growth demand for mobile data services. In this paper, we propose a deep neural networks (DNN) based algorithm for user association and power optimization problem in mmWave heterogeneous network on the basis of gradient iterative algorithm. We jointly design the user association and power optimization to maximize energy efficiency (EE) utilizing Lagrange dual decomposition and then approximate it by DNN models. In addition, an asynchronous distributed DNN based scheme is proposed, which divides the large network model into small distributed networks for distributed data processing on each small base station side to reduce computational time. Simulation results show that the proposed scheme can achieve a high EE with low computation time.

关键词： Optimization Training Computational modeling Data models Machine learning neural networks Resource management

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：