SYMBIOSIS OF HETEROGENEOUS PARALLELISMS

本研究有两个目的：设计一个仿真器，实现共生异构并行和提出新的连接学习算法。在仿真器的实现上，采用了两个工作站。一种是SIMD机制，其中模拟细粒度并行性。另一种是粗粒度的并行，它控制着大量的并行部分。KL 1用于该控制机制。在此共生系统上运行了多下降成本竞争学习算法。研究发现，并行性引起的不确定性对于摆脱坏的局部极小是相当有价值的。为了开发新的学习算法，研究者提出了两种新的方法。在有监督学习中，提出了带附加惩罚的反向传播算法。该算法包括对权重和输出的熵/发散惩罚。在无监督的情况下，首席研究员创建了谐波竞争学习。该算法能够解决多目标优化与自组织的帮助。对数竞争偏置和对数权重变异解决了数据压缩时的局部最优问题，从而完成了本研究项目。

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.