Stochastic-based pattern-recognition analysis

@article{Canals2010StochasticbasedPA,
  title={Stochastic-based pattern-recognition analysis},
  author={V. Canals and A. Morro and J. Rossell{\'o}},
  journal={ArXiv},
  year={2010},
  volume={abs/1202.4495}
}
  • V. Canals, A. Morro, J. Rosselló
  • Published 2010
  • Computer Science
  • ArXiv
  • In this work we review the basic principles of stochastic logic and propose its application to probabilistic-based pattern-recognition analysis. The proposed technique is intrinsically a parallel comparison of input data to various pre-stored categories using Bayesian techniques. We design smart pulse-based stochastic-logic blocks to provide an efficient pattern-recognition analysis. The proposed architecture is applied to a specific navigation problem. 

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    A New Stochastic Computing Methodology for Efficient Neural Network Implementation
    • 49
    Noise-robust hardware implementation of neural networks
    • 3
    A Fast Converging Normalization Unit for Stochastic Computing
    • 3
    • Highly Influenced
    Strained MTJs with latch-based sensing for stochastic computing
    • 2
    Stochastic magnetic tunnel junctions for bioinspired computing

    References

    Publications referenced by this paper.
    SHOWING 1-6 OF 6 REFERENCES
    Pattern Recognition and Machine Learning
    • 8,610
    • PDF
    Random-Pulse Machines
    • 73
    Architecture and statistical model of a pulse-mode digital multilayer neural network
    • 37
    R68-18 Random Pulse Machines
    • 10
    Pattern recognition and machine learning Random pulse machines
    • 1968