Optical competitive learning with, VLSI/liquid-crystal winner-take-all modulators.

@article{Wagner1993OpticalCL,
  title={Optical competitive learning with, VLSI/liquid-crystal winner-take-all modulators.},
  author={K. Wagner and T. Slagle},
  journal={Applied optics},
  year={1993},
  volume={32 8},
  pages={
          1408-35
        }
}
  • K. Wagner, T. Slagle
  • Published 1993
  • Computer Science, Medicine
  • Applied optics
  • A new approach to self-aligning unsupervised optical learning based on the competitive learning algorithm and adaptive holographic interconnectións is introduced. A volume hologram is used to diffract the light from an input spatial light modulator so that it focuses upon a custom winner-take-all very-large-scale-integrated circuit liquid-crystal spatial light modulator. The units that receive the most light switch to a reflective state, and the light reflected from the winning pixels… CONTINUE READING
    25 Citations
    Optical Rectifying Linear Units for Back-Propagation Learning in a Deep Holographic Convolutional Neural Network
    • 2
    Optical finite impulse response neural networks
    Neural network that incorporates direct optical imaging.
    • 1

    References

    SHOWING 1-10 OF 78 REFERENCES
    Multilayer optical learning networks.
    • 167
    • PDF
    Experiments of learning in optical perceptron-like and multilayer neural networks
    • 6
    Winner-take-all spatial light modulator.
    • 16
    Self-organizing optical neural network for unsupervised learning
    • 16