Advertisement

Efficient Implementation of the THSOM Neural Network

  • Rudolf Marek
  • Miroslav Skrbek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5164)

Abstract

Recent trends in microprocessor design clearly show that the multicore processors are the answer to the question how to scale up the processing power of today’s computers. In this article we present our C implementation of the Temporal Hebbian Self-organizing Map (THSOM) neural network. This kind of neural networks have growing computational complexity for larger networks, therefore we present different approaches to the parallel processing – instruction based parallelism and data-based parallelism or their combination. Our C implementation of THSOM is modular and multi-platform, allowing us to move critical parts of the algorithm to other cores, platforms or use different levels of the instruction parallelism yet still run exactly the same computational flows – maintaining good comparability between different setups. For our experiments, we have chosen a multicore x86 system.

Keywords

Network Size Lookup Table Cache Size Temporal Weight Best Match Unit 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kohonen, T.: Self-Organizing Maps3, 3rd edn. Springer, Heidelberg (2001)Google Scholar
  2. 2.
    Koutnik, J.: Inductive Modelling of Temporal Sequences by Means of Self-organization. In: Proceeding of Internation Workshop on Inductive Modelling (IWIM 2007), CTU in Prague, pp. 269–277 (2007) ISBN 978-80-01-03881-9 Google Scholar
  3. 3.
    Koutnik, J.: Self-organizing Maps for Modeling and Recognition of Temporal Sequences, A thesis submitted to Faculty of Electrical Engineering, Czech Technical University in Prague (2008)Google Scholar
  4. 4.
    Porrmann, M., Witkowski, U., Rueckert, U.: A massively parallel architecture for self-organizing feature maps. IEEE Transactions on Neural Networks 14(5), 1110-1121 (2003)CrossRefGoogle Scholar
  5. 5.
    Hendry, D., Duncan, A., Lightowler, A.: Ip core implementation of a self-organizing neural network. IEEE Transactions on Neural Networks 14(5), 1085–1096 (2003)Google Scholar
  6. 6.
    Franzmeier, M., Pohl, C., Porrmann, M., Ruekert, U.: Hardware Accelerated Data Analysis Parallel Computing in Electrical Engineering. In: International Conference on PARELEC 2004, September 7-10, 2004, pp. 309–314 (2004)Google Scholar
  7. 7.
    Rauber, A., Tomsich, P., Merkl, D.: A Parallel Implementation of the Self-Organizing Map Exploiting Cache Effects: Making the SOM Fit for Interactive High-Performance Data Analysis Neural Networks. In: IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Rudolf Marek
    • 1
  • Miroslav Skrbek
    • 1
  1. 1.Department of Computer Science and Engineering, Faculty of Electrical EngineeringCzech Technical University in PraguePragueCzech Republic

Personalised recommendations