이동 에이전트를 이용한 병렬 인공신경망 시뮬레이터
The Parallel ANN(Artificial Neural Network)Simulator using Mobile Agent
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
이 논문은 이동 에이전트 시스템에 기반을 둔 가상의 병렬분산 컴퓨팅 환경에서 병렬로 수행되는 다층 인공신경망 시뮬레이터를 구현하는 것을 목적으로 한다. 다층 신경망은 학습세션, 학습데이터, 계층, 노드, 가중치 수준에서 병렬화가 이루어진다. 이 논문에서는 네트워크의 통신량이 상대적으로 적은 학습세션 및 학습데이터 수준의 병렬화가 가능한 신경망 시뮬레이터를 개발하고 평가하였다. 평가결과, 학습세션 병렬화와 학습데이터 병렬화 성능분석에서 약 3.3배의 학습 수행 성능 향상을 확인할 수 있었다.가상의 병렬 컴퓨터에서 신경망을 병렬로 구현하여 기존의 전용병렬컴퓨터에서 수행한 신경망의 병렬처리와 비슷한 성능을 발휘한다는 점에서 이 논문의 의의가 크다고 할 수 있다. 따라서 가상의 병렬 컴퓨터를 이용하여 신경망을 개발하는데 있어서, 비교적 시간이 많이 소요되는 학습시간을 줄임으로서 신경망 개발에 상당한 도움을 줄 수 있다고 본다.
Abstract
The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data, layer, node, and weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.
참고문헌 (21)
- Nikola B. Serbedzija, "Simulating Artificial Neural Networks on Parallel Architectures", 29(3), pp.56~63 (1996)
- Pacheco P, "Parallel Programming with MPI" (1997), Morgan Kaufmann
- William Gropp, "Using MPI : Portable Parallel Programming with the Message-Passing Interface" (1996), MIT Press
- Danny B.L, "Programming and Deploying Java Mobile Agents with Agelets" (1998), Addison-Wesley
- Mario Tokoro, "Agents : Towards a Society in Which Humans and Computers Cohabitate", pp.1~10 (1995), Springer
- T. R. Ioerger, "Modeling Cooperative, Reactive Behaviors on the Battlefield Using Intelligent Agents", pp.13~23 (2000)
- M. Miller, "Training Teams with Collaborative Agents", pp.63~72 (2000)
- O. Badawy, "Combining neural network knowledge in a mobile collaborating multi-agent system" (2004)
- Manavendra Misra, "Parallel Environments for Implementing Neural Networks", 1, pp.48~60 (1997)
- Gerd Kock, "Simulation of Artificial Neural Networks", 27, pp.15~59 (1996)
- Erich Schikuta, "Structural Data Parallel Neural Network Simulation" (1997)
- X. Zhang,M. Mckenna,J. P. Mesrov, "The backpropagation algorithm on grid and hypercube architectures", 14(3), pp.317~327 (1990)
- A. Zell, "Recent Developments of the SNNS Neural Network Simulator", pp.708~719 (1991)
- C. R. Rosenberg, "An Implementation of Network Learning on the CM", pp.329~340 (1987)
- D. A. Pomerleau, "Neural Network Simulations at Warp Speed: How We Got 17 Million Connections per Second", pp.143~150 (1988)
- J-H. Chung, "A Systolic array Exploiting the Inherent Parallelism of Artificial Neural Networks", 33(3), pp.145~159 (1991)
- R. Straub, "Simulation of backpropagation networks on transputers", 2(5&6), pp.199~208 (1991)
- D. Chess, "Mobile Agents: Are they a good idea?" (1995)
- David Kotz, "Mobile Agents and the Future of the Internet" (1999)
- N. Sundararajan, "Parallel Architectures for Artificial Neural Networks : Paradigms and Implementations", pp.49~ (2002), wiley
- Oh-Kyoung Kwon, "A Grid Resource Allocation System for Scientific Application: Grid Resource Allocation Services Package (GRASP)" (2005)