Abstract
The PPAM is a hardware architecture for a robust, bidirectional and scalable hetero-associative memory. It is fundamentally different from the traditional processing methods which use arithmetic operations and consequently ALUs. In this paper, we present the results of applying the PPAM to a real-world robotics hand-eye coordination task. A comparison is performed with a nearest neighbour technique that was originally used to associate the same dataset. The number of memory load/store operations and the number of ALU operations for the nearest neighbour algorithm is compared with the corresponding PPAM which acheives the same association. It was determined that 29 conflict resolving nodes were required to fully store and recall the entire dataset and the maximum number of memory locations required in any node was 160, with the average and quartiles being much lower.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Amaral, J., Ghosh, J.: An associative memory architecture for concurrent production systems. In: Proc. IEEE International Conference on Systems, Man, and Cybernetics ‘Humans, Information and Technology’, vol. 3, pp. 2219–2224 (1994)
Anzellotti, G., Battiti, R., Lazzizzera, I., Soncini, G., Zorat, A., Sartori, A., Tecchiolli, G., Lee, P.: Totem: a highly parallel chip for triggering applications with inductive learning based on the reactive tabu search. International Journal of Modern Physics C 6(4), 555–560 (1995)
Hebb, D.O.: The Organization of Behavior: A Neuropsychological Theory. Wiley, New York (1949)
Hülse, M., McBride, S., Lee, M.: Robotic hand-eye coordination without global reference: A biologically inspired learning scheme. In: Proc. Int. Conf. on Developmental Learing 2009, China. IEEE Catalog Number: CFP09294 (2009)
Hülse, M., McBride, S., Lee, M.: Fast Learning Mapping Schemes for Robotic HandEye Coordination. Cognitive Computation 2, 1–16 (2010)
Intel: Intel 64 and IA-32 Architectures Optimization Reference Manual. Intel, 248966-024 edition (2011)
Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst. Man Cybern. 18(1), 49–60 (1988)
Lee, P., Costa, E., McBader, S., Clementel, L., Sartori, A.: LogTOTEM: A Logarithmic Neural Processor and its Implementation on an FPGA Fabric. In: International Joint Conference on Neural Networks, IJCNN 2007, pp. 2764–2769 (2007)
Lee, S.W., Kim, J.T., Wang, H.M., Bae, D.J., Lee, K.M., Lee, J.H., Jeon, J.W.: Architecture of RETE Network Hardware Accelerator for Real-Time Context-Aware System. In: Gabrys, B., Howlett, R.J., Jain, L.C. (eds.) KES 2006, Part I. LNCS (LNAI), vol. 4251, pp. 401–408. Springer, Heidelberg (2006)
Moravec, H.: When will Computer Hardware Match the Human Brain? Journal of Evolution and Technology 1 (1998)
Oh, H., Kothari, S.: Adaptation of the relaxation method for learning in bidirectional associative memory. IEEE Trans. Neural Networks 5(4), 576–583 (1994)
Qadir, O., Liu, J., Timmis, J., Tempesti, G., Tyrrell, A.: Principles of Protein Processing for a Self-Organising Associative Memory. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2010), Barcelona, Spain (2010)
Qadir, O., Liu, J., Timmis, J., Tempesti, G., Tyrrell, A.: From Bidirectional Associative Memory to a noise-tolerant, robust Self-Organising Associative Memory. Artificial Intelligence 175(2), 673–693 (2011a)
Qadir, O., Liu, J., Timmis, J., Tempesti, G., Tyrrell, A.: Hardware architecture for a Bidirectional Hetero-Associative Protein Processing Associative Memory. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2011), New Orleans, USA (2011b)
Teich, J.: Invasive Algorithms and Architectures (Invasive Algorithmen und Architekturen). it - Information Technology 50(5), 300–310 (2008)
Toffoli, T.: CAM: A high-performance Cellular Automaton Machine. Physica D 10, 195–204 (1984)
Turing, A.: Computing machinery and intelligence. Mind 59, 433–460 (1950)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Qadir, O., Timmis, J., Tempesti, G., Tyrrell, A. (2012). The Protein Processor Associative Memory on a Robotic Hand-Eye Coordination Task. In: Hart, E., Timmis, J., Mitchell, P., Nakamo, T., Dabiri, F. (eds) Bio-Inspired Models of Networks, Information, and Computing Systems. BIONETICS 2011. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 103. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32711-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-32711-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32710-0
Online ISBN: 978-3-642-32711-7
eBook Packages: Computer ScienceComputer Science (R0)