Hardware architecture of the Protein Processing Associative Memory and the effects of dimensionality and quantisation on performance

Created by W.Langdon from gp-bibliography.bib Revision:1.3949

@Article{Qadir:2014:GPEM,
  author =       "Omer Qadir and Alex Lenz and Gianluca Tempesti and 
                 Jon Timmis and Tony Pipe and Andy Tyrrell",
  title =        "Hardware architecture of the Protein Processing
                 Associative Memory and the effects of dimensionality
                 and quantisation on performance",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2014",
  volume =       "15",
  number =       "3",
  pages =        "245--275",
  month =        sep,
  keywords =     "genetic algorithms, genetic programming, evolvable
                 hardware, Protein processing, PPAM, FPGA, Associative
                 memory, BERT2, Inverse kinematics, Dimensionality,
                 Quantisation, Non-standard computation",
  ISSN =         "1389-2576",
  DOI =          "doi:10.1007/s10710-014-9217-1",
  size =         "30 pages",
  abstract =     "The Protein Processor Associative Memory (PPAM) is a
                 novel hardware architecture for a distributed,
                 decentralised, robust and scalable, bidirectional,
                 hetero-associative memory, that can adapt online to
                 changes in the training data. The PPAM uses the
                 location of data in memory to identify relationships
                 and is therefore fundamentally different from
                 traditional processing methods that tend to use
                 arithmetic operations to perform computation. This
                 paper presents the hardware architecture and details a
                 sample digital logic implementation with an analysis of
                 the implications of using existing techniques for such
                 hardware architectures. It also presents the results of
                 implementing the PPAM for a robotic application that
                 involves learning the forward and inverse kinematics.
                 The results show that, contrary to most other
                 techniques, the PPAM benefits from higher
                 dimensionality of data, and that quantisation intervals
                 are crucial to the performance of the PPAM.",
}

Genetic Programming entries for Omer Qadir Alex Lenz Gianluca Tempesti Jon Timmis Anthony Pipe Andrew M Tyrrell

Citations