SYMBIOSIS OF HETEROGENEOUS PARALLELISMS

异构并行性的共生

• 批准号: 04650301
• 负责人: MATSUYAMA Yasuo
• 金额: $ 1.41万
• 依托单位: IBARAKI UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (C)
• 财政年份: 1992
• 资助国家: 日本
• 起止时间: 1992 至 1993
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-04650301/
• 关键词: Heterogeneous parallelism; Connectionism; Massive parallelism; Learning; Multiple criteria optimization; log-bias; Mutation; Harmonic competition; 教師あり学習; 教師なし学習; ダイバージェンス; 二重並列性; 相利共生; 競合学習; ニューラルネット; 計算論的学習; 自己組織化

This study has a dual purpose : Designing an emulator which realizes symbiosis of heterogeneous parallelisms and presenting new connectionst learning algorithms. On the realization of the emulator, two workstations are used. One is for an SIMD mechanism where a finegrained parallelism is emulated. The other is for a coarse-grained parallelsm which controls the massive parallel part. KL1 was used for this control mechanism. The multiply descent cost competitive learning algorithm was run on this symbiotic system. The nondeterminism caused by the parallelsm was found to be rather meritorious for the exit from bad local minima.For the developement of new learning algorithms, the head investigator presented two major new methods. On the supervised learning, the backpropagation with additional penalties was presented. This algorithm includes entropy/divergence penalties on the weithts and outputs. Pruning of the network and improvement of errors and generalization were acheived.On the unsupervised case, the head investigator created the harmonic competitive learning. This algorithm enables to solve multiple criteria optimization with the aid of self-organization. The logarithmic competition bias and the logarithmic weight mutation solved the local optimality in the case of data compression.Thus, this research project was completed by accomplishing the claimed results.

这项研究有双重目的：设计一个实现异构并行共生的模拟器，并提出新的连接学习算法。在仿真器的实现上，使用了两个工作站。一种是模拟细粒度并行性的 SIMD 机制。另一个是控制大规模并行部分的粗粒度并行。 KL1 用于该控制机制。乘法下降成本竞争学习算法在这个共生系统上运行。人们发现，由并行性引起的不确定性对于摆脱不良局部极小值非常有好处。 对于新学习算法的开发，首席研究员提出了两种主要的新方法。在监督学习上，提出了带有额外惩罚的反向传播。该算法包括对权重和输出的熵/散度惩罚。实现了网络的修剪以及错误和泛化的改进。在无监督的情况下，首席研究员创建了和谐竞争学习。该算法能够借助自组织来解决多标准优化问题。对数竞争偏差和对数权重突变解决了数据压缩情况下的局部最优性。因此，该研究项目通过完成所要求的结果而完成。

项目成果

Y.Matsuyama: "Learning in Competitive Networks with Penalties" Proc.Int.Joint Conf.on Neural Networks. IV. 773-778 (1992)

Y.Matsuyama：“在带有惩罚的竞争网络中学习”Proc.Int.Joint Conf.on Neural Networks。

Y.Matsuyama: "Competitive Learning among Massively Parallel Agents" Neural, Parallel & Scientific Computations. vol.1. 181-198 (1993)

Y.Matsuyama：“大规模并行智能体之间的竞争学习”神经、并行

Y.Matsuyama: "Competitive Learning among Massively Parallel Agents" Neural,Parallel & Scientific Computations. I. 181-198 (1993)

Y.Matsuyama：“大规模并行代理之间的竞争学习”神经，并行

Yasuo Matsuyama: "Learning in competitive networks with penalties" Proc.Int.Joint.Conf.on Neural Networks. IV. 773-778 (1992)

Yasuo Matsuyama：“在有惩罚的竞争网络中学习”Proc.Int.Joint.Conf.on Neural Networks。

Y.Matsuyama: "Laearning in Comptitive Networks with Penalties" Proc.Int.Joint Conf.on Neural Networks. vol.IV. 773-778 (1992)

Y.Matsuyama：“带惩罚的竞争网络中的学习”Proc.Int.Joint Conf.on Neural Networks。