• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.911-931
• /
• 2021

Recently, most cloud services use Docker container environment to provide their services. However, there are no researches to evaluate the performance of communication libraries for multi-GPU based distributed deep learning in a Docker container environment. In this paper, we propose an efficient communication architecture for multi-GPU based deep learning in a Docker container environment by evaluating the performances of various communication libraries. We compare the performances of the parameter server architecture and the All-reduce architecture, which are typical distributed deep learning architectures. Further, we analyze the performances of two separate multi-GPU resource allocation policies - allocating a single GPU to each Docker container and allocating multiple GPUs to each Docker container. We also experiment with the scalability of collective communication by increasing the number of GPUs from one to four. Through experiments, we compare OpenMPI and MPICH, which are representative open source MPI libraries, and NCCL, which is NVIDIA's collective communication library for the multi-GPU setting. In the parameter server architecture, we show that using CUDA-aware OpenMPI with multi-GPU per Docker container environment reduces communication latency by up to 75%. Also, we show that using NCCL in All-reduce architecture reduces communication latency by up to 93% compared to other libraries.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.69-75
• /
• 2021

Recently, deep learning, which is the most used in the field of artificial intelligence, has a structure that is gradually becoming larger and more complex. As the deep learning model grows, a large amount of data is required to learn it, but there are cases in which it is difficult to integrate and learn the data because the data is distributed among several owners and security issues. In that situation we conducted parallel learning for each users that own data and then studied how to integrate it. For this, distributed learning was performed for each owner assuming the security situation as V-environment and H-environment, and the results of distributed learning were integrated using Average, Max, and AbsMax. As a result of applying this to the mnist-fashion data, it was confirmed that there was no significant difference from the results obtained by integrating the data in the V-environment in terms of accuracy. In the H-environment, although there was a difference, meaningful results were obtained.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.34 no.3
• /
• pp.31-34
• /
• 2016

This article reviews Apache SINGA, a general distributed deep learning (DL) platform. The system components and its architecture are presented, as well as how to configure and run SINGA for different types of distributed training using model/data partitioning. Besides, several features and performance are compared with other popular DL tools.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.291-306
• /
• 2020

Nowadays, Data-Network-AI (DNA)-based intelligent services and applications have become a reality to provide a new dimension of services that improve the quality of life and productivity of businesses. Artificial intelligence (AI) can enhance the value of IoT data (data collected by IoT devices). The internet of things (IoT) promotes the learning and intelligence capability of AI. To extract insights from massive volume IoT data in real-time using deep learning, processing capability needs to happen in the IoT end devices where data is generated. However, deep learning requires a significant number of computational resources that may not be available at the IoT end devices. Such problems have been addressed by transporting bulks of data from the IoT end devices to the cloud datacenters for processing. But transferring IoT big data to the cloud incurs prohibitively high transmission delay and privacy issues which are a major concern. Edge computing, where distributed computing nodes are placed close to the IoT end devices, is a viable solution to meet the high computation and low-latency requirements and to preserve the privacy of users. This paper provides a comprehensive review of the current state of leveraging deep learning within edge computing to unleash the potential of IoT big data generated from IoT end devices. We believe that the revision will have a contribution to the development of DNA-based intelligent services and applications. It describes the different distributed training and inference architectures of deep learning models across multiple nodes of the edge computing platform. It also provides the different privacy-preserving approaches of deep learning on the edge computing environment and the various application domains where deep learning on the network edge can be useful. Finally, it discusses open issues and challenges leveraging deep learning within edge computing.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.163-171
• /
• 2021

In this paper, the energy transaction system was optimized by applying a resource allocation algorithm and deep reinforcement learning in the distributed power system. The power demand and supply environment were predicted by deep reinforcement learning. We propose a system that pursues common interests in power trading and increases the efficiency of long-term power transactions in the paradigm shift from conventional centralized to distributed power systems in the power trading system. For a realistic energy simulation model and environment, we construct the energy market by learning weather and monthly patterns adding Gaussian noise. In simulation results, we confirm that the proposed power trading systems are cooperative with each other, seek common interests, and increase profits in the prolonged energy transaction.

• Journal of information and communication convergence engineering
• /
• v.16 no.4
• /
• pp.235-241
• /
• 2018

Recently, deep learning has been actively studied and applied in various fields even to novel writing and painting in ways we could not imagine before. A key feature is that high-performance computing device, especially CUDA-enabled GPU, supports this trend. Researchers who have difficulty accessing such systems fall behind in this fast-changing trend. In this study, we propose and implement a library called Emulearner that helps users to utilize Emulab with ease. Emulab is a research framework equipped with up to thousands of nodes developed by the University of Utah. To use Emulab nodes for deep learning requires a lot of human interactions, however. To solve this problem, Emulearner completely automates operations from authentication of Emulab log-in, node creation, configuration of deep learning to training. By installing Emulearner with a legitimate Emulab account, users can focus on their research on deep learning without hassle.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.205-216
• /
• 2022

One of the many tools used for distributed deep learning training is Kubeflow, which runs on Kubernetes, a container orchestration tool. TensorFlow jobs can be managed using the existing operator provided by Kubeflow. However, when considering the distributed deep learning training jobs based on the parameter server architecture, the scheduling policy used by the existing operator does not consider the task affinity of the distributed training job and does not provide the ability to dynamically allocate or release resources. This can lead to long job completion time and low resource utilization rate. Therefore, in this paper we proposes a new operator that efficiently schedules distributed deep learning training jobs to minimize the job completion time and increase resource utilization rate. We implemented the new operator by modifying the existing operator and conducted experiments to evaluate its performance. The experiment results showed that our scheduling policy improved the average job completion time reduction rate of up to 84% and average CPU utilization increase rate of up to 92%.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.179-199
• /
• 2019

In this paper, we propose optimal methodologies for classifying patent literature by examining various feature extraction methods, machine learning and deep learning models, and provide optimal performance through experiments. We compared the traditional BoW method and a distributed representation method (word embedding vector) as a feature extraction, and compared the morphological analysis and multi gram as the method of constructing the document collection. In addition, classification performance was verified using traditional machine learning model and deep learning model. Experimental results show that the best performance is achieved when we apply the deep learning model with distributed representation and morphological analysis based feature extraction. In Section, Class and Subclass classification experiments, We improved the performance by 5.71%, 18.84% and 21.53%, respectively, compared with traditional classification methods.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.6
• /
• pp.89-96
• /
• 2021

In this study, a deep-learning image analysis model was established and validated for AI-based monitoring of the tidal flat ecosystem for marine protected creatures Ocypode stimpsoni and their habitat. The data in the study was constructed using an unmanned aerial vehicle, and the U-net model was applied for the deep learning model. The accuracy of deep learning model learning results was about 0.76 and about 0.8 each for the Ocypode stimpsoni and their burrow whose accuracy was higher. Analyzing the distribution of crabs and burrows by putting orthomosaic images of the entire study area to the learned deep learning model, it was confirmed that 1,943 Ocypode stimpsoni and 2,807 burrow were distributed in the study area. Through this study, the possibility of using the deep learning image analysis technology for monitoring the tidal ecosystem was confirmed. And it is expected that it can be used in the tidal ecosystem monitoring field by expanding the monitoring sites and target species in the future.