A multi-FPGA architecture for stochastic Restricted Boltzmann Machines

@article{Ly2009AMA,
  title={A multi-FPGA architecture for stochastic Restricted Boltzmann Machines},
  author={Daniel Le Ly and Paul Chow},
  journal={2009 International Conference on Field Programmable Logic and Applications},
  year={2009},
  pages={168-173}
}
  • Daniel Le Ly, Paul Chow
  • Published 2009
  • Computer Science
  • 2009 International Conference on Field Programmable Logic and Applications
  • Although there are many neural network FPGA architectures, there is no framework for designing large, high-performance neural networks suitable for the real world. In this paper, we present two concepts to support a multi-FPGA architecture for stochastic Restricted Boltzmann Machines (RBM), a popular type of neural network. First, a hardware core, called the kth Stage Piecewise Linear Interpolator, is used to implement a high-precision, pipelined function generator. The interpolator increases… CONTINUE READING
    High-Performance Reconfigurable Hardware Architecture for Restricted Boltzmann Machines
    • 57
    • PDF
    A Large-Scale Architecture for Restricted Boltzmann Machines
    • 35
    • PDF
    The challenges of using an embedded MPI for hardware-based processing nodes
    • 16
    • PDF
    Building a multi-FPGA virtualized restricted boltzmann machine architecture using embedded MPI
    • 4
    • PDF
    Accuracy Evaluation of Deep belief Networks with Fixed-Point Arithmetic
    • 7
    • PDF
    PERFORMANCE OF THE FIXED-POINT AUTOENCODER
    • 2
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 11 REFERENCES
    The Impact of Arithmetic Representation on Implementing MLP-BP on FPGAs: A Study
    • 143
    Unsupervised Learning of Distributions of Binary Vectors Using 2-Layer Networks
    • 322
    • PDF
    BEE2: a high-end reconfigurable computing system
    • 316
    • PDF
    Efficient digital implementation of the sigmoid function for reprogrammable logic
    • 140
    • PDF
    A high-performance FPGA architecture for restricted boltzmann machines
    • 29
    • PDF
    Maximally equidistributed combined Tausworthe generators
    • 253
    • PDF
    Artiflcial Neural Networks in Hardware: A Survey
    • 38
    A High-Per formance FPGA Architectu re for Restricted Boltzmann Machines
    • 2009